© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 11-RESID-POST-AA
    11. 59446
    Prev
    Next
    INDEX
    Explanations

    oma

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of the term “melanoma.”

    oai_token-act-pair · o4-mini
    Triggered by @xinyanhu8
    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
    Negative Logits
     buckle
    -0.06
    تيار
    -0.06
     Sail
    -0.06
     Query
    -0.06
     YY
    -0.06
    acier
    -0.06
     böl
    -0.06
    	router
    -0.06
     MatDialog
    -0.06
     Berlin
    -0.06
    POSITIVE LOGITS
    oma
    0.13
    ома
    0.10
    ema
    0.09
    uma
    0.09
    omas
    0.09
    MO
    0.09
    ANGO
    0.08
    ONO
    0.08
    house
    0.08
    ton
    0.08
    Activations Density 0.008%

    No Known Activations