Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 128202
    Prev
    Next
    INDEX
    Explanations

    signaling

    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
    .createComponent
    -0.07
    real
    -0.07
    нуть
    -0.07
    hledem
    -0.06
     sadly
    -0.06
    ¤¤
    -0.06
    fers
    -0.06
    алом
    -0.06
     Allies
    -0.06
    Flip
    -0.06
    POSITIVE LOGITS
    :,
    0.06
     bit
    0.06
     helmet
    0.06
    ="/
    0.06
     banka
    0.06
    ン
    0.06
    [@
    0.06
     také
    0.06
    .makeText
    0.06
     crackers
    0.06
    Activations Density 0.006%

    No Known Activations