© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 79434
    Prev
    Next
    INDEX
    Explanations

    pursue

    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
    ádu
    -0.07
    am
    -0.06
    Br
    -0.06
    Orange
    -0.06
    ainter
    -0.06
     blackout
    -0.06
     організації
    -0.06
    ادات
    -0.06
    ática
    -0.06
     lighting
    -0.06
    POSITIVE LOGITS
     pursuing
    0.14
     pursue
    0.13
     pursued
    0.11
     pursuit
    0.10
     purs
    0.09
     취
    0.09
     pursuits
    0.08
     Purs
    0.08
    Tuy
    0.08
    recipient
    0.07
    Activations Density 0.007%

    No Known Activations