© 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
    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. 5977
    Prev
    Next
    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash

    This neuron detects list-style prompt headings—phrases like “things to…,” “reasons why…,” “review of…,” or “project plan to…” that introduce a numbered or bulleted list of suggestions or reasons.

    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
    yellow
    -0.07
    _selected
    -0.07
    _visible
    -0.07
     endDate
    -0.06
    aeda
    -0.06
    ्रब
    -0.06
    checkbox
    -0.06
    _door
    -0.06
    geometry
    -0.06
    tribution
    -0.06
    POSITIVE LOGITS
    .fromFunction
    0.07
    ました
    0.06
     IHttp
    0.06
     �
    0.06
     Monsanto
    0.06
    (res
    0.06
    HY
    0.06
     pornost
    0.06
    最后
    0.05
    igroup
    0.05
    Activations Density 0.063%

    No Known Activations