© 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. 19-RESID-POST-AA
    11. 111553
    Prev
    Next
    INDEX
    Explanations

    black

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     namoro
    -0.07
    感到
    -0.07
     ngủ
    -0.07
     Sto
    -0.06
     dataIndex
    -0.06
     nargs
    -0.06
     weer
    -0.06
     melt
    -0.06
     uniq
    -0.06
     FA
    -0.06
    POSITIVE LOGITS
     BLACK
    0.08
     black
    0.07
     Black
    0.07
    Members
    0.07
    APON
    0.07
     blocked
    0.07
    Black
    0.07
     Members
    0.07
    ISHED
    0.06
    ाध
    0.06
    Activations Density 0.013%

    No Known Activations