© 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. 19-RESID-POST-AA
    11. 11036
    Prev
    Next
    INDEX
    Explanations

    file

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dec
    -0.08
    Been
    -0.07
     Sal
    -0.07
    solve
    -0.07
    'post
    -0.06
    з
    -0.06
     Time
    -0.06
    ۲۸
    -0.06
     ⟨
    -0.06
     knocking
    -0.06
    POSITIVE LOGITS
    [arr
    0.07
    ฤด
    0.06
    苦
    0.06
     دست
    0.06
    abar
    0.06
    RAL
    0.06
     powerhouse
    0.06
    (sorted
    0.05
    baş
    0.05
    ağ
    0.05
    Activations Density 0.001%

    No Known Activations