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. 94030
    Prev
    Next
    INDEX
    Explanations

    gzip

    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
     preacher
    -0.07
    #pragma
    -0.06
    unication
    -0.06
    ンデ
    -0.06
    Datetime
    -0.06
    �
    -0.06
     Ess
    -0.06
     レ
    -0.06
    อให
    -0.06
     ἀ
    -0.06
    POSITIVE LOGITS
    /rss
    0.07
     gzip
    0.07
    .HttpStatus
    0.07
    Startup
    0.07
    _EMIT
    0.07
    kubectl
    0.07
     push
    0.06
    imize
    0.06
    
    0.06
     malaysia
    0.06
    Activations Density 0.001%

    No Known Activations