© 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. 42562
    Prev
    Next
    INDEX
    Explanations

    data retrieval by ID

    np_max-act · gemini-2.0-flash

    This neuron fires on code-like identifiers and method calls (tokens typical of programming syntax).

    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
     misogyn
    -0.07
    思考
    -0.06
    	Value
    -0.06
     vv
    -0.06
    ly
    -0.06
    Что
    -0.06
    PCR
    -0.06
    スタ
    -0.06
    όγ
    -0.06
    нение
    -0.06
    POSITIVE LOGITS
     Committees
    0.07
     hiệu
    0.06
    алося
    0.06
    (parcel
    0.06
    �장
    0.06
    _attributes
    0.06
    _COMMIT
    0.06
     headlines
    0.06
     Bản
    0.06
     Marseille
    0.06
    Activations Density 0.132%

    No Known Activations