© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55495
    Prev
    Next
    INDEX
    Explanations

    negative healthcare outcomes

    np_max-act · gemini-2.0-flash

    The neuron responds to words that convey intensity, degree, or comparative severity (e.g. “highly,” “vulnerable,” “poorer,” “elevated”).

    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
    /values
    -0.07
    เรา
    -0.06
    crime
    -0.06
     Allocator
    -0.06
    Points
    -0.06
    �게
    -0.06
     RP
    -0.06
    ypes
    -0.06
     fault
    -0.06
    otre
    -0.06
    POSITIVE LOGITS
     edeb
    0.07
    eldom
    0.07
    WSC
    0.07
     oppos
    0.07
    .timeScale
    0.07
    quir
    0.07
     Kurd
    0.06
     gemeins
    0.06
     HttpResponseMessage
    0.06
     conocer
    0.06
    Activations Density 0.056%

    No Known Activations