© 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. 88898
    Prev
    Next
    INDEX
    Explanations

    radiology and imaging

    np_max-act · gemini-2.0-flash

    The neuron flags occurrences of medical-imaging terminology—especially “radiologia” and related imaging modality words.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     سپ
    -0.07
    vl
    -0.07
     合
    -0.06
     mash
    -0.06
    ckett
    -0.06
    [to
    -0.06
     ukáz
    -0.06
     uninstall
    -0.06
     camping
    -0.06
    istically
    -0.06
    POSITIVE LOGITS
     проз
    0.07
     bpm
    0.07
    borah
    0.06
     фин
    0.06
     ενός
    0.06
    )dealloc
    0.06
    .Filters
    0.06
     friendly
    0.06
     kèm
    0.06
    ebin
    0.06
    Activations Density 0.028%

    No Known Activations