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. 23-RESID-POST-AA
    6. 103880
    Prev
    Next
    INDEX
    Explanations

    Code and security terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     concludes
    -0.07
     지난
    -0.07
     зміст
    -0.07
    906
    -0.06
    leasing
    -0.06
    。本
    -0.06
    ''
    -0.06
     concluding
    -0.06
    .anchor
    -0.06
     presently
    -0.06
    POSITIVE LOGITS
    mez
    0.07
     Рег
    0.06
    银
    0.06
    _REC
    0.06
    ंपर
    0.06
    oise
    0.06
    ают
    0.06
     pure
    0.06
    lín
    0.06
    버
    0.06
    Activations Density 0.015%

    No Known Activations