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. 15-RESID-POST-AA
    6. 54080
    Prev
    Next
    INDEX
    Explanations

    Zero

    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
    	reload
    -0.07
     kron
    -0.06
    ,address
    -0.06
     Recap
    -0.06
     joined
    -0.06
    .za
    -0.06
     tř
    -0.06
     tří
    -0.06
     bombs
    -0.06
    .Navigator
    -0.06
    POSITIVE LOGITS
    政治
    0.07
    _assignment
    0.06
     Т
    0.06
    民
    0.06
     playable
    0.06
    Else
    0.06
     ـ
    0.06
    ічна
    0.06
     абсолютно
    0.06
     Gret
    0.06
    Activations Density 0.005%

    No Known Activations