© 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. 75121
    Prev
    Next
    INDEX
    Explanations

    League of Legends

    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
    Computed
    -0.07
    (Window
    -0.07
    .Zoom
    -0.07
     Molecular
    -0.07
     Dust
    -0.06
     Goth
    -0.06
     autobiography
    -0.06
    ierre
    -0.06
    _ALIAS
    -0.06
    _MEMBER
    -0.06
    POSITIVE LOGITS
    ）:
    0.07
    TL
    0.06
    CENT
    0.06
    AMAGE
    0.06
    _ONCE
    0.06
    Fort
    0.06
    _cons
    0.06
     美
    0.06
    liked
    0.06
     Candid
    0.05
    Activations Density 0.006%

    No Known Activations