© 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. 26598
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     trailers
    -0.07
    alten
    -0.06
    )..
    -0.06
     креп
    -0.06
    tty
    -0.06
     Acid
    -0.06
     plastics
    -0.06
    bgcolor
    -0.06
     spolupráci
    -0.06
     Codes
    -0.06
    POSITIVE LOGITS
    ़ें
    0.07
    ADM
    0.07
    rıca
    0.07
    단
    0.06
    umat
    0.06
    lose
    0.06
    numer
    0.06
    >,↵
    0.06
     SEA
    0.06
     كر
    0.06
    Activations Density 0.014%

    No Known Activations