Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 21121
    Prev
    Next
    INDEX
    Explanations

    lets

    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
     đúng
    -0.07
     sæ
    -0.07
     toplum
    -0.07
     DOC
    -0.06
     Мик
    -0.06
     Amph
    -0.06
     LLC
    -0.06
    办
    -0.06
    omik
    -0.06
     Voc
    -0.06
    POSITIVE LOGITS
     yielding
    0.07
    ))↵
    0.07
    ']))↵↵
    0.07
     Overlay
    0.06
    exit
    0.06
    )。↵
    0.06
    ]]↵
    0.06
    _icon
    0.06
     create
    0.06
     trail
    0.06
    Activations Density 0.000%

    No Known Activations