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. 11-RESID-POST-AA
    6. 23944
    Prev
    Next
    INDEX
    Explanations

    This

    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
     despre
    -0.08
    .depend
    -0.07
     touch
    -0.07
    Forest
    -0.07
    _PROFILE
    -0.07
    .square
    -0.07
    _Parms
    -0.06
    hevik
    -0.06
     CROSS
    -0.06
     Sevent
    -0.06
    POSITIVE LOGITS
     This
    0.08
    This
    0.07
     latter
    0.06
     brawl
    0.06
     गत
    0.06
    Similar
    0.06
    oler
    0.06
     운영
    0.06
    >'+
    0.06
     betrayal
    0.06
    Activations Density 0.121%

    No Known Activations