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. 80692
    Prev
    Next
    INDEX
    Explanations

    text

    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
     APR
    -0.06
     Marshall
    -0.06
     Jan
    -0.06
     audiences
    -0.06
    gov
    -0.06
     Wer
    -0.06
     Community
    -0.06
    mar
    -0.06
    ania
    -0.06
     Lost
    -0.06
    POSITIVE LOGITS
    onnement
    0.07
    /entities
    0.06
    	cat
    0.06
     Kenny
    0.06
     iframe
    0.06
    采用
    0.06
    وبی
    0.06
    affer
    0.06
     Ens
    0.06
     땅
    0.06
    Activations Density 0.001%

    No Known Activations