© 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. 74688
    Prev
    Next
    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash

    The neuron activates on four-digit year tokens (e.g. “1923,” “1937,” “1940,” etc.).

    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
    ゞ
    -0.08
     ماند
    -0.06
    after
    -0.06
    rends
    -0.06
    orque
    -0.06
    eyim
    -0.06
    σίας
    -0.06
     Cal
    -0.06
    hone
    -0.06
     Cu
    -0.06
    POSITIVE LOGITS
    |#
    0.07
     {:.
    0.06
    incible
    0.06
     ########.
    0.06
     applaud
    0.06
    .deepcopy
    0.06
     forgiving
    0.06
     sql
    0.06
    	Runtime
    0.06
    لعاب
    0.06
    Activations Density 0.041%

    No Known Activations