© 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. 92167
    Prev
    Next
    INDEX
    Explanations

    commas/brackets

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric data in tables—especially decimal‐formatted measurements or statistics.

    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
    Fo
    -0.07
    	content
    -0.06
    _TESTS
    -0.06
    =res
    -0.06
    >false
    -0.06
     चलत
    -0.06
    بوب
    -0.06
    计划
    -0.06
     lang
    -0.06
    /Math
    -0.06
    POSITIVE LOGITS
    Calling
    0.07
     Amendment
    0.07
    -small
    0.07
    %m
    0.07
    mé
    0.06
     क
    0.06
    Upgrade
    0.06
    ningen
    0.06
    _instruction
    0.06
    QWidget
    0.06
    Activations Density 0.217%

    No Known Activations