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. 19-RESID-POST-AA
    6. 9961
    Prev
    Next
    INDEX
    Explanations

    narrative

    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
    oph
    -0.07
    论
    -0.06
     JMenuItem
    -0.06
     liệu
    -0.06
     tenant
    -0.06
    你
    -0.06
     Christian
    -0.06
    omore
    -0.06
    altet
    -0.06
    chio
    -0.06
    POSITIVE LOGITS
     reverted
    0.06
     muff
    0.06
     Quote
    0.06
     Ha
    0.06
     キ
    0.06
     منطقه
    0.06
     Sund
    0.06
     uncomfortable
    0.06
     drill
    0.06
    amoto
    0.06
    Activations Density 0.035%

    No Known Activations