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. 69580
    Prev
    Next
    INDEX
    Explanations

    rights

    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
    utory
    -0.07
     земель
    -0.07
    ervers
    -0.06
     btc
    -0.06
    isce
    -0.06
    erves
    -0.06
     علم
    -0.06
     systematic
    -0.06
     tisí
    -0.06
    inc
    -0.06
    POSITIVE LOGITS
    arton
    0.07
    recipient
    0.07
    ブリ
    0.06
     Sig
    0.06
    .Multi
    0.06
    .flatten
    0.06
    nova
    0.06
     Sax
    0.06
    ONGLONG
    0.06
    winner
    0.06
    Activations Density 0.005%

    No Known Activations