© 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. 35228
    Prev
    Next
    INDEX
    Explanations

    on

    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
    �
    -0.07
     Chill
    -0.07
    वत
    -0.06
    _norm
    -0.06
     suppress
    -0.06
    анси
    -0.06
     binge
    -0.06
    weights
    -0.06
    Instant
    -0.06
     onClick
    -0.06
    POSITIVE LOGITS
    prises
    0.08
    CategoryId
    0.06
     vista
    0.06
    spě
    0.06
     historically
    0.06
     numar
    0.06
    .writeHead
    0.06
    obbled
    0.06
     všechny
    0.06
    рал
    0.06
    Activations Density 0.005%

    No Known Activations