© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 95325
    Prev
    Next
    INDEX
    Explanations

    in

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cater
    -0.07
    (css
    -0.06
    (_
    -0.06
    �果
    -0.06
     seo
    -0.06
     مست
    -0.06
    ,H
    -0.06
     HttpResponseMessage
    -0.06
     receptor
    -0.06
    site
    -0.06
    POSITIVE LOGITS
    	insert
    0.07
    /rules
    0.06
     crate
    0.06
    _radi
    0.06
     peut
    0.06
    >',↵
    0.06
    IVES
    0.06
    (express
    0.06
     oversees
    0.06
     xmin
    0.06
    Activations Density 0.073%

    No Known Activations