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. 104312
    Prev
    Next
    INDEX
    Explanations

    sic

    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
    _water
    -0.07
    人才
    -0.06
    flu
    -0.06
     ave
    -0.06
    gons
    -0.06
    etta
    -0.06
     až
    -0.06
     smelled
    -0.06
    하시
    -0.06
    =?",
    -0.06
    POSITIVE LOGITS
    ics
    0.07
    [jj
    0.07
    [channel
    0.06
     بخش
    0.06
    (power
    0.06
    [new
    0.06
     faults
    0.06
    Picture
    0.06
    getDate
    0.06
    _METADATA
    0.06
    Activations Density 0.001%

    No Known Activations