Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55319
    Prev
    Next
    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “time” (and closely related mentions of the time concept).

    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
    Proj
    -0.06
     Spice
    -0.06
    써
    -0.06
    สหร
    -0.06
    Pdf
    -0.06
    ập
    -0.06
    olecular
    -0.06
    priv
    -0.05
    optimize
    -0.05
    avail
    -0.05
    POSITIVE LOGITS
     DOUBLE
    0.08
    [],↵
    0.07
    .currentTimeMillis
    0.07
     parameter
    0.07
     IMPORTANT
    0.07
     bytearray
    0.07
     게
    0.07
    _CUSTOMER
    0.07
     appeared
    0.06
     месте
    0.06
    Activations Density 0.006%

    No Known Activations