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. 7-RESID-POST-AA
    6. 85996
    Prev
    Next
    INDEX
    Explanations

    art studios

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     빛
    -0.07
    boru
    -0.07
    _representation
    -0.07
    opot
    -0.07
     Islands
    -0.06
    enarios
    -0.06
     současné
    -0.06
    _side
    -0.06
     Invasion
    -0.06
    .sort
    -0.06
    POSITIVE LOGITS
     workshop
    0.10
     Workshop
    0.07
     Vis
    0.07
     laboratories
    0.07
     де
    0.06
     handbook
    0.06
     Wh
    0.06
     stressing
    0.06
    avenport
    0.06
    Md
    0.06
    Activations Density 0.007%

    No Known Activations