© 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. 68874
    Prev
    Next
    INDEX
    Explanations

    disorders

    np_max-act · gemini-2.0-flash

    medical terminology related to Alzheimer's disease and its treatment.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects mentions of the “Diagnostic and Statistical Manual of Mental Disorders” (DSM) or similar formal diagnostic‐manual references.

    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
    "We
    -0.07
    -spin
    -0.06
    bounding
    -0.06
    .font
    -0.06
    .OUT
    -0.06
     tasting
    -0.06
    .SOCK
    -0.06
     iron
    -0.06
    φη
    -0.06
     국민
    -0.06
    POSITIVE LOGITS
    ８
    0.07
    HashCode
    0.06
     �
    0.06
     adequate
    0.06
    онах
    0.06
    يان
    0.06
    ीतर
    0.06
    inecraft
    0.06
     impaired
    0.06
     deset
    0.06
    Activations Density 0.005%

    No Known Activations