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. 15-RESID-POST-AA
    6. 10742
    Prev
    Next
    INDEX
    Explanations

    ers

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    *>(
    -0.07
    ุก
    -0.06
    浪
    -0.06
     út
    -0.06
     Cao
    -0.06
     UIT
    -0.06
    ingredient
    -0.06
    >().
    -0.06
    _ax
    -0.06
     males
    -0.06
    POSITIVE LOGITS
    -million
    0.07
     ден
    0.06
    Sorting
    0.06
    ving
    0.06
    ship
    0.06
    ignite
    0.06
     display
    0.06
    Æ
    0.06
    (TAG
    0.06
    leurs
    0.06
    Activations Density 0.039%

    No Known Activations