© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 56044
    Prev
    Next
    INDEX
    Explanations

    version control

    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
    .Speed
    -0.07
    coles
    -0.07
    SW
    -0.06
    ानसभ
    -0.06
    _SCROLL
    -0.06
    Mbps
    -0.06
    ↵				↵
    -0.06
    COMP
    -0.06
     Innovation
    -0.06
    \Factory
    -0.06
    POSITIVE LOGITS
    inging
    0.07
    ساس
    0.06
     sanctioned
    0.06
     پای
    0.06
    send
    0.06
     очевид
    0.06
     кислот
    0.06
     topLeft
    0.06
    ورات
    0.06
    hya
    0.06
    Activations Density 0.023%

    No Known Activations