© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 51767
    Prev
    Next
    INDEX
    Explanations

    identical

    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
     uterus
    -0.07
     reproductive
    -0.07
     scream
    -0.06
    ,application
    -0.06
     usern
    -0.06
     favourable
    -0.06
    Captain
    -0.06
     Granny
    -0.06
     sauces
    -0.06
    sched
    -0.06
    POSITIVE LOGITS
    IDDLE
    0.06
    ONGO
    0.06
     метою
    0.06
    امت
    0.06
     Москва
    0.06
    еться
    0.06
    anol
    0.06
    leşme
    0.06
    ासन
    0.06
     mại
    0.06
    Activations Density 0.003%

    No Known Activations