© 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. 92502
    Prev
    Next
    INDEX
    Explanations

    considered

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of statistical significance statements, especially phrases around p-value thresholds (e.g. “p < 0.05 was considered significant”).

    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
    Fac
    -0.08
     Kant
    -0.07
    shell
    -0.07
    Sheet
    -0.06
     aeros
    -0.06
    jsx
    -0.06
    Seg
    -0.06
     lunches
    -0.06
     deviations
    -0.06
    LR
    -0.06
    POSITIVE LOGITS
     Friedrich
    0.07
    ोष
    0.06
     الاس
    0.06
     strlen
    0.06
    取り
    0.06
     samozřejmě
    0.06
    虽然
    0.06
     جمع
    0.06
    adia
    0.06
    828
    0.06
    Activations Density 0.005%

    No Known Activations