© 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. 129549
    Prev
    Next
    INDEX
    Explanations

    Scientific and technical

    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
     PT
    -0.08
    (beta
    -0.07
    364
    -0.07
     CONTRIBUT
    -0.07
     fre
    -0.07
     dudes
    -0.06
    oute
    -0.06
    .bulk
    -0.06
    olocation
    -0.06
    403
    -0.06
    POSITIVE LOGITS
     væ
    0.06
     polož
    0.06
     tung
    0.06
     laten
    0.06
     Recognition
    0.06
    のか
    0.06
    .getInput
    0.06
    .setContent
    0.06
    )obj
    0.06
    )return
    0.06
    Activations Density 0.271%

    No Known Activations