© 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. 12451
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    This neuron flags tokens related to the “Yes/No” factual-consistency verdict (e.g. “Yes,” “No,” or “factually consistent”).

    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
     Сем
    -0.07
     Insight
    -0.06
    âu
    -0.06
    Unfortunately
    -0.06
    inp
    -0.06
    -kind
    -0.06
    Analyzer
    -0.05
     Conversely
    -0.05
     Mas
    -0.05
    豪
    -0.05
    POSITIVE LOGITS
     Treasury
    0.09
    <!--
    0.07
    raising
    0.07
     Viet
    0.07
     이러한
    0.06
     evac
    0.06
    xbd
    0.06
    ntag
    0.06
     πέ
    0.06
     btnCancel
    0.06
    Activations Density 0.010%

    No Known Activations