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. 80992
    Prev
    Next
    INDEX
    Explanations

    Speed (mph)

    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
     evangel
    -0.06
     casa
    -0.06
    大利
    -0.06
    管
    -0.06
     majestic
    -0.06
     tutorial
    -0.06
    خت
    -0.06
    คว
    -0.05
    �
    -0.05
     interceptor
    -0.05
    POSITIVE LOGITS
    licts
    0.08
    ी.
    0.07
    	found
    0.07
    hydr
    0.07
     ;
    0.07
    _lens
    0.07
    *time
    0.07
     sufferers
    0.07
    override
    0.07
     yr
    0.06
    Activations Density 0.003%

    No Known Activations