© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55962
    Prev
    Next
    INDEX
    Explanations

    February dates

    np_max-act · gemini-2.0-flash

    This neuron detects the date header tokens (the month–day markers) at the start of each post, i.e. the “February <day>” lines identifying a blog entry’s date.

    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
     QStringLiteral
    -0.07
    .index
    -0.07
    /fl
    -0.07
     thus
    -0.06
    .getX
    -0.06
     vhodné
    -0.06
     modify
    -0.06
     confused
    -0.06
    upt
    -0.06
    _community
    -0.06
    POSITIVE LOGITS
     NAV
    0.07
    คล
    0.06
    انيا
    0.06
     çoğu
    0.06
    홍
    0.06
    &p
    0.06
    Instrument
    0.06
     Chand
    0.06
    ício
    0.06
    Vertices
    0.06
    Activations Density 0.003%

    No Known Activations