© 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. 11-RESID-POST-AA
    11. 52998
    Prev
    Next
    INDEX
    Explanations

    memorandum opinion and order

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     अत
    -0.07
     operating
    -0.07
     mega
    -0.07
    ních
    -0.07
    frared
    -0.06
     APIs
    -0.06
    _scale
    -0.06
    _width
    -0.06
    _der
    -0.06
     bugs
    -0.06
    POSITIVE LOGITS
     crown
    0.06
     Tacoma
    0.06
     placebo
    0.06
     Edmonton
    0.06
     poco
    0.06
    举
    0.06
    issors
    0.06
    palette
    0.06
    bat
    0.06
     foresee
    0.06
    Activations Density 0.003%

    No Known Activations