© 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. 61178
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    ーの
    -0.07
    SSERT
    -0.07
    期間
    -0.07
     responseType
    -0.07
    /thread
    -0.06
     podstat
    -0.06
    개를
    -0.06
     numbers
    -0.06
     INCIDENT
    -0.06
    avelength
    -0.06
    POSITIVE LOGITS
     Philosoph
    0.06
    Division
    0.06
    oultry
    0.06
     Opt
    0.06
    -friendly
    0.06
     Ell
    0.06
    ierre
    0.06
    '),
    0.06
    bit
    0.06
    Cap
    0.06
    Activations Density 0.011%

    No Known Activations