© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 91375
    Prev
    Next
    INDEX
    Explanations

    198

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     benefited
    -0.06
     але
    -0.06
    	body
    -0.06
     이는
    -0.06
     も
    -0.06
    出版社
    -0.06
    гар
    -0.06
    답
    -0.06
    rello
    -0.05
    ρεια
    -0.05
    POSITIVE LOGITS
    (PR
    0.07
    anggal
    0.07
    nox
    0.07
    (low
    0.07
     Kendrick
    0.07
     Aunt
    0.07
    pch
    0.06
    -(
    0.06
    $log
    0.06
    (Command
    0.06
    Activations Density 0.000%

    No Known Activations