© 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. 68943
    Prev
    Next
    INDEX
    Explanations

    million

    np_max-act · gemini-2.0-flash

    The neuron identifies numeric expressions that specify temporal measurements or geological ages (e.g. “million years ago,” numeric dates, and similar time markers).

    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
    ुड
    -0.07
    하지
    -0.06
    REFERENCES
    -0.06
     Bunun
    -0.06
    .Table
    -0.06
    謝
    -0.06
    　　　　　　　　　　　　
    -0.06
     gibi
    -0.06
    CEE
    -0.06
    bcd
    -0.06
    POSITIVE LOGITS
    .fill
    0.06
     veloc
    0.06
     streamline
    0.06
     قتل
    0.06
     strained
    0.06
     elapsedTime
    0.06
     geo
    0.06
    @Json
    0.06
     コ
    0.06
    (Debug
    0.06
    Activations Density 0.005%

    No Known Activations