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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 93374
    Prev
    Next
    INDEX
    Explanations

    ValueError

    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
    fern
    -0.07
    арх
    -0.07
     chân
    -0.07
    елич
    -0.07
    jian
    -0.06
    .cast
    -0.06
    έλ
    -0.06
    polation
    -0.06
    INST
    -0.06
     галуз
    -0.06
    POSITIVE LOGITS
     ValueError
    0.11
    QWidget
    0.08
     dissolve
    0.07
     Cout
    0.06
     Sent
    0.06
    tar
    0.06
    .BorderSide
    0.06
     disposition
    0.06
     Lay
    0.06
     Fehler
    0.06
    Activations Density 0.002%

    No Known Activations