© 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. 7-RESID-POST-AA
    11. 97608
    Prev
    Next
    INDEX
    Explanations

    Explaining/discussing points

    np_max-act · gemini-2.0-flash
    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
     reun
    -0.07
     proper
    -0.07
    _track
    -0.06
    -all
    -0.06
    Logical
    -0.06
    Stage
    -0.06
    ่างๆ
    -0.06
    piration
    -0.06
    НО
    -0.06
    ssid
    -0.06
    POSITIVE LOGITS
    ück
    0.06
     ROOM
    0.06
    评论
    0.06
     igual
    0.06
     Thông
    0.06
     земель
    0.06
     گفت
    0.06
     oprav
    0.06
     노하우
    0.06
    <Value
    0.06
    Activations Density 0.131%

    No Known Activations