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. 113533
    Prev
    Next
    INDEX
    Explanations

    Code and documentation

    np_max-act · gemini-2.0-flash

    tokens that are parts of file paths, filenames, or other code/documentation structural markup.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     müzik
    -0.06
    帮助
    -0.06
     receptor
    -0.06
    _TEST
    -0.06
    opers
    -0.06
    났
    -0.06
    lığı
    -0.06
    Vault
    -0.05
     привод
    -0.05
     {:.
    -0.05
    POSITIVE LOGITS
     sagen
    0.07
    weg
    0.06
     member
    0.06
    гар
    0.06
    со
    0.06
     khỏ
    0.06
     collagen
    0.06
     جر
    0.06
     Например
    0.06
    ogra
    0.06
    Activations Density 1.195%

    No Known Activations