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. 87038
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    sumer
    -0.06
    ْر
    -0.06
     converged
    -0.06
    。しかし
    -0.06
    exist
    -0.06
    (ib
    -0.06
     причины
    -0.06
    。そして
    -0.05
    zeitig
    -0.05
    letes
    -0.05
    POSITIVE LOGITS
    HeaderCode
    0.07
     remarkable
    0.07
     dří
    0.07
    ´:
    0.07
    Clear
    0.07
    jah
    0.07
    맞
    0.06
    perl
    0.06
     enforce
    0.06
    .white
    0.06
    Activations Density 0.313%

    No Known Activations