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

    Neuronpedia

    Jacobian LensNEW
    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. 57074
    Prev
    Next
    INDEX
    Explanations

    report

    np_max-act · gemini-2.0-flash

    This neuron detects French words and phrases related to the synthesis and reporting of results (e.g. “synthèse,” “rédaction d’un rapport de synthèse,” “présentation des résultats”).

    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
    .Callback
    -0.07
    perimental
    -0.07
     approach
    -0.06
    -offset
    -0.06
    counter
    -0.06
     descent
    -0.06
    Кон
    -0.06
     قض
    -0.06
    .sy
    -0.06
    Stroke
    -0.06
    POSITIVE LOGITS
     valves
    0.09
    ือง
    0.07
    �
    0.07
     electrónico
    0.07
    _reason
    0.06
    ній
    0.06
     userProfile
    0.06
     самостоятельно
    0.06
     Schn
    0.06
     assists
    0.06
    Activations Density 0.039%

    No Known Activations