© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 18650
    Prev
    Next
    INDEX
    Explanations

    et

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PLE
    -0.07
    -fly
    -0.07
    Mail
    -0.07
    y
    -0.07
     dalla
    -0.06
    ilk
    -0.06
    -black
    -0.06
    acro
    -0.06
    ्य
    -0.06
    ampa
    -0.06
    POSITIVE LOGITS
     et
    0.14
     couldn
    0.09
    ET
    0.09
     ET
    0.09
     letting
    0.08
     at
    0.08
     ев
    0.08
    et
    0.08
    редел
    0.08
    [at
    0.08
    Activations Density 0.023%

    No Known Activations