© 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. 52251
    Prev
    Next
    INDEX
    Explanations

    Code and general text

    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
     Campo
    -0.07
    ルク
    -0.07
     cot
    -0.07
     Karel
    -0.06
    _SUP
    -0.06
    番号
    -0.06
    isure
    -0.06
    (alert
    -0.06
    udd
    -0.06
    esseract
    -0.06
    POSITIVE LOGITS
     son
    0.07
    Source
    0.06
     Level
    0.06
    245
    0.06
    Process
    0.06
     зрения
    0.06
    ระเบ
    0.05
     exec
    0.05
     bravery
    0.05
     bird
    0.05
    Activations Density 0.000%

    No Known Activations