© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 34275
    Prev
    Next
    INDEX
    Explanations

    study

    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
     Christine
    -0.06
     Barbie
    -0.06
     Finger
    -0.06
     Bra
    -0.06
     Courtney
    -0.06
     xcb
    -0.06
     Мед
    -0.06
     breat
    -0.06
     žádné
    -0.06
     Wax
    -0.06
    POSITIVE LOGITS
     interpol
    0.07
    '}}>↵
    0.07
    twig
    0.06
    累
    0.06
    �
    0.06
     devis
    0.06
     deltaTime
    0.06
    	q
    0.06
    taş
    0.06
     imposition
    0.06
    Activations Density 0.011%

    No Known Activations