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. 81020
    Prev
    Next
    INDEX
    Explanations

    cream

    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
     BER
    -0.07
    맹
    -0.07
     digitalWrite
    -0.07
    .upload
    -0.07
    CHAR
    -0.06
     bw
    -0.06
    تع
    -0.06
    '''↵
    -0.06
    	that
    -0.06
    UDIO
    -0.06
    POSITIVE LOGITS
     mois
    0.07
     click
    0.07
     aerospace
    0.06
     OC
    0.06
    Courier
    0.06
    حدة
    0.06
     FHA
    0.06
    .newaxis
    0.06
    crets
    0.06
     evolve
    0.06
    Activations Density 0.019%

    No Known Activations