© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 89583
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    terms related to software package imports and class definitions in programming code.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects organization or vendor identifiers in code import/package paths (e.g. domain-style prefixes like “com.sequenceiq”, “org.apache.cassandra”, “github.com/pingcap”, “mongo/base/…”, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -------------↵
    -0.07
    Toy
    -0.07
    ############
    -0.06
    \Cache
    -0.06
    ……」↵↵
    -0.06
     pop
    -0.06
     Macron
    -0.06
     hardwood
    -0.06
    디시
    -0.06
    ByVersion
    -0.06
    POSITIVE LOGITS
     indust
    0.07
     wager
    0.06
    Views
    0.06
    ))]↵
    0.06
     Liberties
    0.06
     )↵↵↵
    0.06
    (sent
    0.06
    tuple
    0.06
     Range
    0.06
     keeper
    0.06
    Activations Density 0.007%

    No Known Activations