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. 15-RESID-POST-AA
    6. 24768
    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_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
     racially
    -0.06
     záv
    -0.06
     Guides
    -0.06
     Kov
    -0.06
    $n
    -0.06
     Moff
    -0.06
    getY
    -0.06
    LEC
    -0.06
    όγ
    -0.06
    *scale
    -0.06
    POSITIVE LOGITS
     Timestamp
    0.07
    、二
    0.07
     regrets
    0.07
     readme
    0.06
    .XtraEditors
    0.06
    <File
    0.06
     sucked
    0.06
     whole
    0.06
    ":"+
    0.06
     Poke
    0.06
    Activations Density 0.000%

    No Known Activations