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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 11-RESID-POST-AA
    6. 99459
    Prev
    Next
    INDEX
    Explanations

    time

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Weekly
    -0.08
    but
    -0.07
    pra
    -0.07
    ‪
    -0.07
    Are
    -0.07
     GIS
    -0.06
     dve
    -0.06
    tracts
    -0.06
     fazla
    -0.06
    }while
    -0.06
    POSITIVE LOGITS
    rup
    0.07
    gis
    0.06
    vasion
    0.06
     інститут
    0.06
    -heavy
    0.06
     Rem
    0.06
     mềm
    0.06
    mits
    0.06
    uds
    0.06
    /parser
    0.06
    Activations Density 0.006%

    No Known Activations