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. 9565
    Prev
    Next
    INDEX
    Explanations

    rule

    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
    oucí
    -0.07
     feasibility
    -0.07
    ddd
    -0.06
    apsible
    -0.06
    くん
    -0.06
     nuevas
    -0.06
     глуб
    -0.06
     flu
    -0.06
     barrel
    -0.06
     preferably
    -0.06
    POSITIVE LOGITS
     RULE
    0.06
    Piece
    0.06
    せて
    0.06
    ');
    ↵
    ↵
    0.06
     GG
    0.06
     usr
    0.06
     helping
    0.06
    :id
    0.06
    habit
    0.06
     Michelle
    0.06
    Activations Density 0.021%

    No Known Activations