© 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. 5842
    Prev
    Next
    INDEX
    Explanations

    Thursday

    np_max-act · gemini-2.0-flash

    This neuron detects day‐of‐week labels (e.g. “Monday,” “Thursday,” “Wednesday”) in document datelines.

    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
    1
    -0.08
    ۱
    -0.07
    Max
    -0.07
     frags
    -0.07
     мод
    -0.06
     Ban
    -0.06
    0
    -0.06
    61
    -0.06
     antigen
    -0.06
    ５
    -0.06
    POSITIVE LOGITS
     Tuesday
    0.11
     Wednesday
    0.11
     Thursday
    0.10
    Thursday
    0.09
    uesday
    0.09
    Tuesday
    0.09
     Tues
    0.07
    ês
    0.07
     dateString
    0.07
    cargo
    0.07
    Activations Density 0.011%

    No Known Activations