© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 13609
    Prev
    Next
    INDEX
    Explanations

    unusual

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the words “cruel” and “unusual” (as in “cruel and unusual punishment”).

    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
     badges
    -0.07
     Kore
    -0.07
    768
    -0.07
    AME
    -0.07
    URRED
    -0.06
    'm
    -0.06
     vra
    -0.06
    (re
    -0.06
    ByteBuffer
    -0.06
    _DEV
    -0.06
    POSITIVE LOGITS
    είου
    0.07
     Information
    0.07
    泉
    0.07
    ubl
    0.06
     health
    0.06
     معد
    0.06
     innovation
    0.06
    JT
    0.06
    edl
    0.06
     Innovation
    0.06
    Activations Density 0.001%

    No Known Activations