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. 78878
    Prev
    Next
    INDEX
    Explanations

    opinions and expertise

    np_max-act · gemini-2.0-flash

    mentions of expert consultation or professional opinion used to verify, assess, or explain something

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    ensitive
    -0.06
     finalists
    -0.06
     columnist
    -0.06
     sensitive
    -0.06
     سازی
    -0.06
    /simple
    -0.06
    Threshold
    -0.06
    染
    -0.06
    ATTER
    -0.06
     Hashtable
    -0.06
    POSITIVE LOGITS
    ROUND
    0.07
    Added
    0.07
    rais
    0.07
    (hours
    0.07
    国際
    0.07
    �
    0.07
     zů
    0.07
    �
    0.07
    วรรณ
    0.06
    OfWork
    0.06
    Activations Density 0.072%

    No Known Activations