© 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. 129979
    Prev
    Next
    INDEX
    Explanations

    study

    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
     энерг
    -0.07
    していた
    -0.07
    _BB
    -0.06
    内部
    -0.06
    #elif
    -0.06
    _percent
    -0.06
     приблиз
    -0.06
    eyh
    -0.06
     datap
    -0.06
     tow
    -0.06
    POSITIVE LOGITS
     study
    0.07
     investigation
    0.07
     Study
    0.06
    nest
    0.06
     denial
    0.06
     hashing
    0.06
     demonstration
    0.06
    START
    0.06
    jang
    0.06
     classification
    0.06
    Activations Density 0.023%

    No Known Activations