© 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. 15-RESID-POST-AA
    11. 83559
    Prev
    Next
    INDEX
    Explanations

    technical discussions

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thought
    -0.06
     руку
    -0.06
    ガ
    -0.06
     Jam
    -0.06
     được
    -0.06
     대해서
    -0.06
    路径
    -0.06
    Colon
    -0.06
    (Collision
    -0.05
    (padding
    -0.05
    POSITIVE LOGITS
     thriving
    0.07
    >All
    0.07
    /Add
    0.06
    _excel
    0.06
    _hresult
    0.06
     Dmit
    0.06
    ный
    0.06
     clashed
    0.06
    ????????
    0.06
    -team
    0.06
    Activations Density 0.000%

    No Known Activations