© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 35493
    Prev
    Next
    INDEX
    Explanations

    hull

    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
    Fall
    -0.07
     Burlington
    -0.07
     ent
    -0.06
     بیشتر
    -0.06
     καν
    -0.06
    TextColor
    -0.06
     Destroy
    -0.06
     CLUB
    -0.06
     nozzle
    -0.06
    )sender
    -0.06
    POSITIVE LOGITS
    主義
    0.07
    	priv
    0.06
    <|begin_of_text|>
    0.06
     Transitional
    0.06
    $values
    0.06
     lamps
    0.06
     Исп
    0.06
    .Db
    0.06
    .struts
    0.06
     leasing
    0.06
    Activations Density 0.000%

    No Known Activations