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. 85696
    Prev
    Next
    INDEX
    Explanations

    span

    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
     Neh
    -0.07
     میدان
    -0.07
    Restore
    -0.07
    κου
    -0.06
    (New
    -0.06
     Bron
    -0.06
    bk
    -0.06
    맹
    -0.06
    岡
    -0.06
     Fro
    -0.06
    POSITIVE LOGITS
    ALSE
    0.06
    angen
    0.06
     unidentified
    0.06
    arov
    0.06
    atable
    0.06
    auction
    0.06
    actable
    0.06
    :expr
    0.06
     подой
    0.06
    stm
    0.06
    Activations Density 0.008%

    No Known Activations