Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 55095
    Prev
    Next
    INDEX
    Explanations

    ephemerality

    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
    ấc
    -0.07
    /ss
    -0.06
    通过
    -0.06
     پروژه
    -0.06
    啪
    -0.06
    ;q
    -0.06
    薩
    -0.06
    setTitle
    -0.06
    رس
    -0.06
    rowning
    -0.06
    POSITIVE LOGITS
     gameObject
    0.08
    (){↵
    0.07
    (coords
    0.07
    (cps
    0.07
    价格
    0.06
     MUCH
    0.06
     lawful
    0.06
    _Callback
    0.06
     mundane
    0.06
     thought
    0.06
    Activations Density 0.020%

    No Known Activations