© 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. 34188
    Prev
    Next
    INDEX
    Explanations

    object

    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
    (dialog
    -0.06
     úda
    -0.06
     таких
    -0.06
     currentItem
    -0.06
    デル
    -0.06
     filings
    -0.06
    ollo
    -0.06
     Applicants
    -0.06
    aint
    -0.06
     operated
    -0.06
    POSITIVE LOGITS
    _Insert
    0.07
    ncias
    0.07
     amendments
    0.07
    899
    0.06
     Sm
    0.06
     thaw
    0.06
    ursions
    0.06
     sta
    0.06
    996
    0.06
    Cla
    0.06
    Activations Density 0.004%

    No Known Activations