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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-RESID-POST-AA
    6. 81273
    Prev
    Next
    INDEX
    Explanations

    strength, protection, resistance

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -aff
    -0.07
    _crc
    -0.06
     Warcraft
    -0.06
     pepper
    -0.06
    osal
    -0.06
    ời
    -0.06
     Tristan
    -0.06
    azaar
    -0.06
    нике
    -0.06
    platform
    -0.06
    POSITIVE LOGITS
    ]))↵↵
    0.07
     Да
    0.06
     veel
    0.06
     {↵↵↵
    0.06
     necesita
    0.06
     {}↵↵↵
    0.06
     impressed
    0.06
    .setDescription
    0.06
     IHttp
    0.06
    pbs
    0.06
    Activations Density 0.236%

    No Known Activations