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. 7-RESID-POST-AA
    6. 100728
    Prev
    Next
    INDEX
    Explanations

    anxiety

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     derp
    -0.07
     HMS
    -0.07
     فارس
    -0.07
    杉
    -0.07
     coupe
    -0.07
    ollywood
    -0.07
     profile
    -0.07
     رس
    -0.07
     отд
    -0.07
     lé
    -0.07
    POSITIVE LOGITS
     anxiety
    0.16
     Anxiety
    0.15
     anxious
    0.12
     anx
    0.11
    xiety
    0.10
    :Any
    0.07
    196
    0.06
     anom
    0.06
     Apex
    0.06
     возника
    0.06
    Activations Density 0.006%

    No Known Activations