© 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. 113274
    Prev
    Next
    INDEX
    Explanations

    O

    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
     pipes
    -0.07
    INCT
    -0.07
    _SUPPORT
    -0.07
    versation
    -0.06
    .Angle
    -0.06
     Ace
    -0.06
    abling
    -0.06
     sled
    -0.06
     Fair
    -0.06
     Practices
    -0.06
    POSITIVE LOGITS
     Theodore
    0.07
    $p
    0.06
    .,↵
    0.06
     leaned
    0.06
    Juan
    0.06
    DidAppear
    0.06
    Cons
    0.06
    &quot
    0.06
    京都
    0.06
    SpinBox
    0.06
    Activations Density 0.004%

    No Known Activations