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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19-RESID-POST-AA
    6. 83501
    Prev
    Next
    INDEX
    Explanations

    cpp

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getQuery
    -0.07
    べ
    -0.07
     weed
    -0.06
    Series
    -0.06
    there
    -0.06
     standing
    -0.06
    ']))↵
    -0.06
    -unstyled
    -0.06
    202
    -0.06
    esinden
    -0.06
    POSITIVE LOGITS
     till
    0.07
     Traditional
    0.07
    .blank
    0.06
     gymn
    0.06
    execution
    0.06
     такий
    0.06
    ční
    0.06
     traditional
    0.06
    (cps
    0.06
    孔
    0.06
    Activations Density 0.000%

    No Known Activations