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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12614
    Prev
    Next
    INDEX
    Explanations

    %

    np_max-act · gemini-2.0-flash

    The neuron activates on the square‐bracketed calendar labels (like “[Today at]”, “[Tomorrow at]”, “[Hier à]”, etc.) used in locale configuration files to mark relative date/time phrases.

    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
    _words
    -0.07
    .Patient
    -0.07
    NX
    -0.07
    (hit
    -0.06
     eve
    -0.06
    еред
    -0.06
    isAdmin
    -0.06
     murderers
    -0.06
    589
    -0.06
     Flutter
    -0.06
    POSITIVE LOGITS
     climb
    0.07
    _SYN
    0.06
     lifestyle
    0.06
     variables
    0.06
    黃
    0.06
     هنر
    0.06
     proces
    0.06
     trò
    0.06
     conflicts
    0.06
    νη
    0.06
    Activations Density 0.001%

    No Known Activations