© 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. 120333
    Prev
    Next
    INDEX
    Explanations

    behavior

    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
    оки
    -0.06
     Holding
    -0.06
    (TAG
    -0.06
     上
    -0.06
    agers
    -0.06
    绩
    -0.06
     almış
    -0.06
    religious
    -0.06
     Inspiration
    -0.06
     Celsius
    -0.06
    POSITIVE LOGITS
     bouts
    0.07
    alsy
    0.07
     Faul
    0.06
    .UserInfo
    0.06
    -conf
    0.06
     CS
    0.06
    왕
    0.06
     Behavioral
    0.06
    tout
    0.06
    .charset
    0.06
    Activations Density 0.007%

    No Known Activations