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. 87050
    Prev
    Next
    INDEX
    Explanations

    +

    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
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iscard
    -0.07
     Hük
    -0.06
    Javascript
    -0.06
     discard
    -0.06
     CLR
    -0.06
     �
    -0.06
    річ
    -0.06
    ienne
    -0.06
     petroleum
    -0.06
    '):↵
    -0.06
    POSITIVE LOGITS
     happy
    0.08
     SCI
    0.07
     junction
    0.06
    сп
    0.06
    Boston
    0.06
    �
    0.06
    ------+
    0.06
    Processor
    0.06
    vp
    0.06
     Multip
    0.06
    Activations Density 0.002%

    No Known Activations