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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 15-RESID-POST-AA
    6. 25172
    Prev
    Next
    INDEX
    Explanations

    one

    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
    论坛
    -0.07
     yasak
    -0.07
     Anal
    -0.07
     ROW
    -0.07
     duration
    -0.06
    *)
    -0.06
     *));↵
    -0.06
    	print
    -0.06
     угл
    -0.06
    _break
    -0.06
    POSITIVE LOGITS
     Californ
    0.06
    .appcompat
    0.06
    186
    0.06
    252
    0.06
     deepest
    0.06
    ishes
    0.06
    Česk
    0.06
    xfd
    0.06
    abbreviation
    0.05
    have
    0.05
    Activations Density 0.000%

    No Known Activations