© 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
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 123173
    Prev
    Next
    INDEX
    Explanations

    underscore

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jiří
    -0.08
     خص
    -0.07
     ludicrous
    -0.07
     폐
    -0.06
     فس
    -0.06
    /DTD
    -0.06
    ariance
    -0.06
     Gh
    -0.06
    Mode
    -0.06
    -eye
    -0.06
    POSITIVE LOGITS
     _
    0.07
    (Global
    0.06
     __
    0.06
     _.
    0.06
     isLoading
    0.06
    _rights
    0.06
     нев
    0.06
    elenium
    0.06
    лив
    0.06
    지는
    0.06
    Activations Density 0.008%

    No Known Activations