© 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. 56742
    Prev
    Next
    INDEX
    Explanations

    presentation descriptions

    np_max-act · gemini-2.0-flash

    The neuron detects future‐oriented presentation cues—words like “will,” “show,” “learn,” “describe,” and similar verbs used in talk/session abstracts to announce what’s coming.

    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
     Atl
    -0.07
     bitch
    -0.06
    dition
    -0.06
     informative
    -0.06
    fil
    -0.06
     amounts
    -0.06
     текст
    -0.06
    worth
    -0.06
     possess
    -0.06
     Sevilla
    -0.06
    POSITIVE LOGITS
     standardUserDefaults
    0.07
     суспіль
    0.06
    _WORDS
    0.06
     curly
    0.06
    .prepare
    0.06
    ，只
    0.06
    _COMMON
    0.06
     combineReducers
    0.06
     只
    0.06
    าศาสตร
    0.06
    Activations Density 0.038%

    No Known Activations