© 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. 124872
    Prev
    Next
    INDEX
    Explanations

    withholding information

    np_max-act · gemini-2.0-flash

    The neuron lights up on words and phrases about disclosing or withholding information—e.g. “share,” “can’t,” “give…away,” “reveal,” “cannot talk about.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    conversations involving deception and manipulation.

    oai_token-act-pair · gpt-4o-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
    дон
    -0.07
    -collapse
    -0.07
    elo
    -0.07
    Clo
    -0.06
    market
    -0.06
     BPM
    -0.06
    Ian
    -0.06
     Michaels
    -0.06
    vection
    -0.06
    ้าหน
    -0.06
    POSITIVE LOGITS
     Matters
    0.07
     состоянии
    0.07
     lr
    0.06
     галуз
    0.06
    owment
    0.06
    auses
    0.06
     Volunteers
    0.06
     Transit
    0.06
    \Middleware
    0.06
    ؟؟
    0.06
    Activations Density 0.030%

    No Known Activations