© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126116
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on numeric expressions—years, percentages, statistics, and other multi-digit numbers.

    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
     Mona
    -0.07
    脱
    -0.07
     SIMD
    -0.06
    _advanced
    -0.06
    战
    -0.06
    ltra
    -0.06
     εκ
    -0.06
     NVIDIA
    -0.06
     Pornhub
    -0.06
    uname
    -0.06
    POSITIVE LOGITS
     redundant
    0.07
     enthusiastic
    0.07
     pristine
    0.07
    -description
    0.06
    (sizeof
    0.06
     portrayed
    0.06
     RELATED
    0.06
    skill
    0.06
    ARGET
    0.06
     movie
    0.06
    Activations Density 0.126%

    No Known Activations