© 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. 12745
    Prev
    Next
    INDEX
    Explanations

    null/false values

    np_max-act · gemini-2.0-flash

    The neuron is triggered by literal null/NULL (and similarly literal false) return values in code.

    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
    ANGO
    -0.07
    SAME
    -0.06
     snprintf
    -0.06
    Division
    -0.06
    PCODE
    -0.06
    bserv
    -0.06
    ثیر
    -0.06
    grading
    -0.06
    time
    -0.06
     перей
    -0.06
    POSITIVE LOGITS
     Yatırım
    0.08
    μαι
    0.08
     village
    0.07
     """↵↵
    0.07
    !↵↵↵
    0.06
    บก
    0.06
    **
    ↵
    0.06
     Playground
    0.06
     Lansing
    0.06
    ++){↵↵
    0.06
    Activations Density 0.010%

    No Known Activations