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. 15-RESID-POST-AA
    6. 21644
    Prev
    Next
    INDEX
    Explanations

    technical/patent documentation

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     خان
    -0.07
     Reve
    -0.07
    	pm
    -0.06
     TERMS
    -0.06
    Net
    -0.06
     preempt
    -0.06
     pubkey
    -0.06
    Consum
    -0.06
    (Graph
    -0.06
    Half
    -0.06
    POSITIVE LOGITS
    uisse
    0.07
     тради
    0.07
     wang
    0.06
     stati
    0.06
     appropri
    0.06
     pigs
    0.06
    );$
    0.06
    ота
    0.06
     رنگ
    0.06
     neuen
    0.06
    Activations Density 0.166%

    No Known Activations