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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6228
    Prev
    Next
    INDEX
    Explanations

    Adverbs/adjectives ending in "ive"

    np_max-act · gemini-2.0-flash

    This neuron detects discourse-level cue words or phrases (like “Intuitively,” “However,” “In other words,” etc.) that signal explanations or transitions.

    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
     thinly
    -0.06
     knull
    -0.06
     Joy
    -0.06
    존
    -0.06
     Derived
    -0.06
    Stop
    -0.06
     далі
    -0.06
    _VOLUME
    -0.06
     flap
    -0.06
     destruction
    -0.06
    POSITIVE LOGITS
    (pd
    0.08
     antique
    0.06
    per
    0.06
    ิกา
    0.06
    /mat
    0.06
    :absolute
    0.06
    antom
    0.06
     Вот
    0.06
    .'.$
    0.06
    横
    0.06
    Activations Density 0.029%

    No Known Activations