Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 104310
    Prev
    Next
    INDEX
    Explanations

    There

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hitters
    -0.07
    Sarah
    -0.06
     neuro
    -0.06
     insanely
    -0.06
     sınav
    -0.06
     am
    -0.06
     interview
    -0.06
     referees
    -0.06
    Videos
    -0.06
    άκ
    -0.06
    POSITIVE LOGITS
     doctr
    0.07
    avras
    0.06
    oco
    0.06
    .ToString
    0.06
    Щ
    0.06
     marshaller
    0.06
    ,count
    0.06
    Shown
    0.06
    Added
    0.06
    Ă
    0.06
    Activations Density 0.025%

    No Known Activations