© 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. 15-RESID-POST-AA
    11. 128960
    Prev
    Next
    INDEX
    Explanations

    Ontario

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     overcoming
    -0.07
    {k
    -0.06
     cave
    -0.06
    (gl
    -0.06
    ({↵
    -0.06
    {x
    -0.06
    -x
    -0.06
    [x
    -0.06
    coins
    -0.06
    ज
    -0.06
    POSITIVE LOGITS
     Toronto
    0.13
     Ontario
    0.13
    Toronto
    0.11
    enso
    0.07
     Melbourne
    0.07
     Walmart
    0.07
     Ont
    0.07
     те
    0.07
     Burlington
    0.07
    ーボ
    0.07
    Activations Density 0.007%

    No Known Activations