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. 7-RESID-POST-AA
    6. 93280
    Prev
    Next
    INDEX
    Explanations

    consider

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _multiple
    -0.07
     patriotism
    -0.06
    Drop
    -0.06
    /dist
    -0.06
     ABOUT
    -0.06
    (formatter
    -0.06
    (length
    -0.06
     charged
    -0.06
    ために
    -0.06
    leaf
    -0.06
    POSITIVE LOGITS
     consider
    0.07
    getOrElse
    0.07
     XCTAssertTrue
    0.06
     taşıy
    0.06
     intl
    0.06
    _bill
    0.06
    consider
    0.06
     Dynamo
    0.06
    도를
    0.06
    ’app
    0.06
    Activations Density 0.052%

    No Known Activations