© 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 (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 112076
    Prev
    Next
    INDEX
    Explanations

    course

    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
     dangers
    -0.07
    -tier
    -0.07
     Electoral
    -0.07
     attachment
    -0.07
     intrigued
    -0.07
     Pointer
    -0.07
     Bangkok
    -0.07
     ideal
    -0.06
     Flying
    -0.06
    (W
    -0.06
    POSITIVE LOGITS
    (proc
    0.06
    .phi
    0.06
    ูม
    0.06
    �
    0.06
    カテゴリ
    0.06
    _MARKER
    0.06
     functools
    0.06
    groundColor
    0.06
    geben
    0.06
     startIndex
    0.06
    Activations Density 0.039%

    No Known Activations