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. 79506
    Prev
    Next
    INDEX
    Explanations

    Arena

    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
     testimony
    -0.07
     dre
    -0.06
    getInt
    -0.06
     μ
    -0.06
     cm
    -0.06
     invent
    -0.06
     mess
    -0.06
     distancia
    -0.06
    ан
    -0.06
     Knock
    -0.06
    POSITIVE LOGITS
    $pdf
    0.07
     ISC
    0.06
     Kurds
    0.06
     faiz
    0.06
     ess
    0.06
    Bubble
    0.06
     �
    0.06
    _CONSOLE
    0.06
     Kurdistan
    0.06
    roje
    0.06
    Activations Density 0.020%

    No Known Activations