© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 55784
    Prev
    Next
    INDEX
    Explanations

    now

    np_max-act · gemini-2.0-flash

    This neuron detects references to the present moment or temporary states, especially the word "now" and the phrase "for now."

    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
    ственный
    -0.07
     minutos
    -0.07
     credits
    -0.07
     alguns
    -0.06
    atório
    -0.06
    oglobin
    -0.06
     English
    -0.06
     Dollars
    -0.06
     заболева
    -0.06
    нити
    -0.06
    POSITIVE LOGITS
    alaxy
    0.07
    قل
    0.07
     honeymoon
    0.06
    ＾
    0.06
    (strings
    0.06
    .restore
    0.06
     vox
    0.06
     zajímav
    0.06
    ROUND
    0.06
    디
    0.06
    Activations Density 0.014%

    No Known Activations