© 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. 95367
    Prev
    Next
    INDEX
    Explanations

    offer

    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
     political
    -0.06
     republiky
    -0.06
    lates
    -0.06
     treasury
    -0.06
    تماد
    -0.06
     survivor
    -0.06
     bottoms
    -0.06
     suspended
    -0.06
     surviving
    -0.06
    (search
    -0.06
    POSITIVE LOGITS
     offer
    0.13
     Offer
    0.13
    Offer
    0.10
     offerings
    0.09
     offered
    0.08
     Idea
    0.07
    offer
    0.07
     offre
    0.07
     Johan
    0.07
    xdc
    0.07
    Activations Density 0.022%

    No Known Activations