© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 12678
    Prev
    Next
    INDEX
    Explanations

    handwriting

    np_max-act · gemini-2.0-flash

    This neuron specifically detects mentions of handwriting (e.g. the word “handwriting” or closely related handwriting contexts).

    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
    (In
    -0.06
    edení
    -0.06
     Cinema
    -0.06
     Vect
    -0.06
    +"/"+
    -0.06
    ışman
    -0.06
     yaşam
    -0.06
    (Player
    -0.06
    (int
    -0.06
     böl
    -0.06
    POSITIVE LOGITS
     handwriting
    0.07
    CppMethodPointer
    0.07
    -tip
    0.06
    ΥΝ
    0.06
     wrought
    0.06
    。
    0.06
    _EMIT
    0.06
    PIP
    0.06
    影
    0.06
    Should
    0.06
    Activations Density 0.015%

    No Known Activations