© 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. 7-RESID-POST-AA
    6. 120808
    Prev
    Next
    INDEX
    Explanations

    solutions or answers

    np_max-act · gemini-2.0-flash

    tokens that belong to the assistant's reply (i.e., model-generated assistant message content).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rangle
    -0.07
     jButton
    -0.07
     Elena
    -0.07
     Kč
    -0.07
    経
    -0.07
    -no
    -0.07
    ítulo
    -0.07
     k
    -0.07
    ání
    -0.07
    انا
    -0.06
    POSITIVE LOGITS
    े↵
    0.06
     Employer
    0.06
    _saved
    0.06
     methodology
    0.06
     değiştir
    0.06
     Pew
    0.05
     π
    0.05
    manager
    0.05
    (pop
    0.05
    _serialize
    0.05
    Activations Density 0.050%

    No Known Activations