© 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. 29609
    Prev
    Next
    INDEX
    Explanations

    improvement

    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
    _REGS
    -0.06
    야
    -0.06
    wcs
    -0.06
    .*?)
    -0.06
     systematically
    -0.05
    zs
    -0.05
    �자
    -0.05
    กฎ
    -0.05
     anus
    -0.05
    Deserialize
    -0.05
    POSITIVE LOGITS
     amendments
    0.08
    标准
    0.07
    Sarah
    0.07
     supreme
    0.07
     Amendment
    0.07
     reforms
    0.07
     Mike
    0.07
     improvements
    0.07
     improvement
    0.07
     amendment
    0.07
    Activations Density 0.020%

    No Known Activations