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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 89757
    Prev
    Next
    INDEX
    Explanations

    conjunctions and commas

    np_max-act · gemini-2.0-flash

    This neuron detects terms related to analytic metrics or measurement (e.g. visitor behavior, traffic sources, conversion rates).

    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
    now
    -0.07
    door
    -0.06
     throat
    -0.06
     slugg
    -0.06
    ivet
    -0.06
    _misc
    -0.06
    -parse
    -0.06
     gor
    -0.06
     Temple
    -0.06
     QFont
    -0.06
    POSITIVE LOGITS
    erece
    0.07
     применения
    0.07
    .On
    0.07
     investigative
    0.06
    禮
    0.06
    Qi
    0.06
    resentation
    0.06
    )));
    0.06
     застосування
    0.06
    のに
    0.06
    Activations Density 0.069%

    No Known Activations