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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 26549
    Prev
    Next
    INDEX
    Explanations

    ken

    np_max-act · gemini-2.0-flash

    medical terminology related to physical conditions and symptoms.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on nationality labels in parentheses (e.g. “(Hebrew)”, “(Italian)”), marking the parenthesized country/ethnicity tags following personal names.

    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
    'https
    -0.07
     dále
    -0.07
    PIO
    -0.07
     करक
    -0.06
     đứ
    -0.06
     naar
    -0.06
     Pelosi
    -0.06
    Several
    -0.06
    .mem
    -0.06
    RSS
    -0.06
    POSITIVE LOGITS
     getS
    0.07
    \S
    0.06
    )),
    0.06
     Balls
    0.06
    {_
    0.06
     qualify
    0.06
    fo
    0.06
    (TM
    0.06
    _way
    0.06
    NSBundle
    0.06
    Activations Density 0.039%

    No Known Activations