© 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. 126328
    Prev
    Next
    INDEX
    Explanations

    code assertions

    np_max-act · gemini-2.0-flash

    information related to unit testing frameworks and code structures.

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

    This neuron fires on programming‐style syntax—i.e. identifiers, keywords, and punctuation from code snippets.

    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
     primarily
    -0.06
    ])))↵
    -0.06
     loading
    -0.06
     van
    -0.06
    Crop
    -0.06
    @↵↵
    -0.06
    .’”↵↵
    -0.06
     params
    -0.06
    _FIFO
    -0.06
    大全
    -0.06
    POSITIVE LOGITS
     ben
    0.07
     суспіль
    0.07
    Yahoo
    0.07
     quam
    0.06
     battleground
    0.06
    National
    0.06
    —we
    0.06
    -court
    0.06
    (cert
    0.06
    Corporate
    0.06
    Activations Density 0.055%

    No Known Activations