© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6332
    Prev
    Next
    INDEX
    Explanations

    Common English words

    np_max-act · gemini-2.0-flash

    The neuron fires on instructional or procedural phrasing—i.e. clauses that give advice or describe how or when to do something.

    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
    -bin
    -0.07
    mil
    -0.07
     Updated
    -0.06
    /")↵
    -0.06
    .bg
    -0.06
    laden
    -0.06
    Change
    -0.06
     Publication
    -0.06
    -calendar
    -0.06
    薄
    -0.06
    POSITIVE LOGITS
     skyline
    0.06
     mọi
    0.06
    ORMAT
    0.06
     factura
    0.06
     citt
    0.06
     XIV
    0.06
     Cumhur
    0.06
    Specifier
    0.06
     асп
    0.06
    خاص
    0.06
    Activations Density 0.652%

    No Known Activations