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. 128886
    Prev
    Next
    INDEX
    Explanations

    is

    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
     lý
    -0.06
    灰
    -0.06
     trous
    -0.06
     ten
    -0.06
    odu
    -0.06
    wash
    -0.06
     Linden
    -0.06
     transf
    -0.06
     sausage
    -0.06
     built
    -0.06
    POSITIVE LOGITS
    _dirs
    0.07
    Network
    0.07
    �로
    0.06
    .Lerp
    0.06
    .innerHeight
    0.06
     Blackhawks
    0.06
     상담
    0.06
     totals
    0.06
     Bí
    0.06
     defaultstate
    0.06
    Activations Density 0.019%

    No Known Activations