© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 94650
    Prev
    Next
    INDEX
    Explanations

    chrome

    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
    apiro
    -0.06
    ()),
    -0.06
    瀬
    -0.06
     Yaz
    -0.06
     patents
    -0.06
     WK
    -0.06
     Playboy
    -0.06
    进行
    -0.06
    Kent
    -0.06
    ρία
    -0.06
    POSITIVE LOGITS
    chrome
    0.07
    صب
    0.07
    chal
    0.06
     Буд
    0.06
    lub
    0.06
    .tw
    0.06
    \Modules
    0.06
    τε
    0.06
     Monter
    0.06
    ятия
    0.06
    Activations Density 0.001%

    No Known Activations