© 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. 6363
    Prev
    Next
    INDEX
    Explanations

    Source code or web content

    np_max-act · gemini-2.0-flash

    This neuron specifically fires on date‐ and time‐stamp elements (e.g. day names, numeric dates, times, and related punctuation) in RSS/XML metadata.

    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
     penalty
    -0.07
    868
    -0.06
    672
    -0.06
     imgUrl
    -0.06
     Toplam
    -0.06
    ############################################################
    -0.06
    liğinde
    -0.06
    ●
    -0.06
    /Subthreshold
    -0.06
    ingga
    -0.06
    POSITIVE LOGITS
     utilizado
    0.07
    ере
    0.07
     brass
    0.07
    専
    0.07
    کس
    0.06
    omap
    0.06
    TEL
    0.06
    ेशन
    0.06
    行動
    0.06
     час
    0.06
    Activations Density 0.003%

    No Known Activations