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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 3-RESID-POST-AA
    6. 121982
    Prev
    Next
    INDEX
    Explanations

    .S

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -Aug
    -0.07
     chickens
    -0.07
    ثير
    -0.06
    IFS
    -0.06
    [f
    -0.06
     toplum
    -0.06
     ViewState
    -0.06
    /issues
    -0.06
    Art
    -0.06
     alk
    -0.06
    POSITIVE LOGITS
    .S
    0.08
     sanitize
    0.06
    Calcul
    0.06
     nudity
    0.06
     xls
    0.06
    ActionButton
    0.06
    ्थल
    0.06
    IAL
    0.06
    .multipart
    0.06
     preload
    0.06
    Activations Density 0.002%

    No Known Activations