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. 103548
    Prev
    Next
    INDEX
    Explanations

    taken

    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
    	progress
    -0.06
     شاه
    -0.06
     americ
    -0.06
    -Д
    -0.06
    Potential
    -0.06
     affordable
    -0.06
     strike
    -0.06
    _DR
    -0.06
    (tags
    -0.06
    鹿
    -0.06
    POSITIVE LOGITS
    GetY
    0.07
    pc
    0.07
    cx
    0.06
    kehr
    0.06
    awning
    0.06
    //{{
    0.06
    .getLogin
    0.06
     impart
    0.06
    .Use
    0.06
     }}>↵
    0.06
    Activations Density 0.019%

    No Known Activations