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. 73337
    Prev
    Next
    INDEX
    Explanations

    Scrapbooking/crafting blog posts

    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
     PropertyChangedEventArgs
    -0.07
    	then
    -0.06
    >>)
    -0.06
    >manual
    -0.06
    SqlParameter
    -0.06
    луата
    -0.06
    	duration
    -0.05
    _datasets
    -0.05
     summarize
    -0.05
     sklearn
    -0.05
    POSITIVE LOGITS
    (IP
    0.07
    --------------
    0.07
    ोब
    0.07
    ROAD
    0.06
    ตรวจ
    0.06
    Depart
    0.06
    ulously
    0.06
    UGH
    0.06
    _Ad
    0.06
    osto
    0.06
    Activations Density 0.052%

    No Known Activations