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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 108833
    Prev
    Next
    INDEX
    Explanations

    question/end punctuation

    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
     grote
    -0.07
    .ge
    -0.07
    チェ
    -0.06
    年に
    -0.06
    راف
    -0.06
    افق
    -0.06
    Вт
    -0.06
     Ot
    -0.06
     mega
    -0.06
    -len
    -0.06
    POSITIVE LOGITS
    황
    0.07
    (EXPR
    0.06
    亚
    0.06
    .dec
    0.06
    im
    0.06
    smith
    0.06
    icult
    0.06
     accuracy
    0.06
     Gujar
    0.06
     titanium
    0.06
    Activations Density 0.002%

    No Known Activations