© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 45846
    Prev
    Next
    INDEX
    Explanations

    ke

    np_max-act · gemini-2.0-flash

    the neuron detects numeric tokens — digits, numbers and numeric-looking strings (including decimals, years, and numeric field values).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     Balanced
    -0.07
    olumes
    -0.07
    }>↵
    -0.07
    commended
    -0.07
    .output
    -0.07
    -connect
    -0.07
    .component
    -0.07
    Exec
    -0.06
    (correct
    -0.06
    .Settings
    -0.06
    POSITIVE LOGITS
     rejects
    0.06
     beasts
    0.06
    <TreeNode
    0.06
     그냥
    0.06
     absurd
    0.06
     Alto
    0.06
     Bone
    0.06
     Freddy
    0.06
     Honestly
    0.06
     chiếc
    0.06
    Activations Density 4.479%

    No Known Activations