© 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. 115060
    Prev
    Next
    INDEX
    Explanations

    Questionable code characters

    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
    usp
    -0.07
    ingham
    -0.07
     disclosures
    -0.06
    んです
    -0.06
    Square
    -0.06
     [{'
    -0.06
     sand
    -0.06
    Maps
    -0.06
     ownership
    -0.06
    weight
    -0.06
    POSITIVE LOGITS
     multif
    0.07
     objectAtIndex
    0.07
    .MaximizeBox
    0.07
     Auxiliary
    0.06
     controlId
    0.06
    krvldkf
    0.06
    گاب
    0.06
    (coll
    0.06
     ať
    0.06
     тай
    0.06
    Activations Density 0.048%

    No Known Activations