Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 74886
    Prev
    Next
    INDEX
    Explanations

    code variable

    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
     Uk
    -0.07
        
    -0.07
     خدمت
    -0.07
     underst
    -0.06
     incre
    -0.06
    icions
    -0.06
    _PAR
    -0.06
    tolower
    -0.06
     Unidos
    -0.06
     없었다
    -0.06
    POSITIVE LOGITS
     поможет
    0.06
     tức
    0.06
    ened
    0.06
    므로
    0.06
     behaved
    0.06
     проблема
    0.06
     suede
    0.06
     resin
    0.06
     flying
    0.06
    lanır
    0.06
    Activations Density 0.004%

    No Known Activations