© 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. 30060
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    brick
    -0.07
    _nd
    -0.07
    tmp
    -0.06
    toHaveBeenCalledWith
    -0.06
     Nhĩ
    -0.06
     stable
    -0.06
     Outcome
    -0.06
    Green
    -0.06
     setIs
    -0.06
    .friends
    -0.06
    POSITIVE LOGITS
     pc
    0.06
     Kv
    0.06
     logical
    0.06
     swirling
    0.06
     observational
    0.06
    /stdc
    0.06
    .interfaces
    0.05
     Hệ
    0.05
     detailed
    0.05
    uido
    0.05
    Activations Density 0.012%

    No Known Activations