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. 87095
    Prev
    Next
    INDEX
    Explanations

    home or house

    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
    Sur
    -0.07
    tam
    -0.06
    �
    -0.06
    follow
    -0.06
    Ted
    -0.06
    _alias
    -0.06
    Cond
    -0.06
    _UTIL
    -0.06
     příjem
    -0.06
    	layer
    -0.06
    POSITIVE LOGITS
     παρα
    0.07
     постоянно
    0.07
    grass
    0.06
    ัดส
    0.06
    [Int
    0.06
     entsprech
    0.06
     (/
    0.06
    Salvar
    0.06
     Snape
    0.06
    _aes
    0.06
    Activations Density 0.045%

    No Known Activations