© 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. 89780
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens in advisory or rule‐based contexts—i.e. when the text is giving instructions, guidelines, safety advice, or describing enforcement of rules.

    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
    .requireNonNull
    -0.07
    .publisher
    -0.06
    primir
    -0.06
    carrier
    -0.06
    (UInt
    -0.06
    setVisible
    -0.06
    .transfer
    -0.06
     ROM
    -0.06
    233
    -0.06
     eliminate
    -0.06
    POSITIVE LOGITS
     noct
    0.07
    _connections
    0.07
     пы
    0.06
     Quite
    0.06
    opot
    0.06
     평당
    0.06
    *w
    0.06
     unconventional
    0.06
     arist
    0.06
     tucked
    0.06
    Activations Density 0.169%

    No Known Activations