© 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. 6184
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    This neuron detects discourse markers and transition words (e.g. “if,” “so,” “well,” etc.) that signal logical or rhetorical shifts.

    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
    .getJSONObject
    -0.06
     Levitra
    -0.06
    jišť
    -0.06
    _LP
    -0.06
    952
    -0.06
    azaar
    -0.06
    tiler
    -0.06
     BLUE
    -0.06
    Nm
    -0.06
    린이
    -0.06
    POSITIVE LOGITS
    ritable
    0.07
    철
    0.06
     lexical
    0.06
     nodes
    0.06
    cept
    0.06
    .Here
    0.06
     ча
    0.06
    uations
    0.06
     deut
    0.06
     inconsistencies
    0.06
    Activations Density 0.128%

    No Known Activations