© 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. 30462
    Prev
    Next
    INDEX
    Explanations

    C

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of class or struct field declarations—that is, member variable names (e.g. identifiers like mShared, mOtherInfo, mHLen) in code.

    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
    _streams
    -0.06
     tyre
    -0.06
     md
    -0.06
    dux
    -0.06
     breakpoint
    -0.06
    _cust
    -0.06
    .Mode
    -0.06
     yog
    -0.06
     Champions
    -0.06
    atility
    -0.06
    POSITIVE LOGITS
     membres
    0.06
    握
    0.06
     Од
    0.06
     cellpadding
    0.06
     метою
    0.06
    angered
    0.06
     treff
    0.06
     lety
    0.06
     زي
    0.06
     imageView
    0.06
    Activations Density 0.026%

    No Known Activations