© 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. 11-RESID-POST-AA
    11. 77736
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs

    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
    AMILY
    -0.07
     geçti
    -0.07
    enarios
    -0.06
     Tasmania
    -0.06
    thing
    -0.06
    uncated
    -0.06
    _import
    -0.06
     wr
    -0.06
     paramString
    -0.06
     cname
    -0.06
    POSITIVE LOGITS
    صول
    0.07
     Hermes
    0.07
     Criterion
    0.07
     Фор
    0.07
    Merc
    0.06
     marque
    0.06
     ************************
    0.06
     پیش
    0.06
     \
    0.06
     центра
    0.06
    Activations Density 0.110%

    No Known Activations