© 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. 7923
    Prev
    Next
    INDEX
    Explanations

    said

    np_max-act · gemini-2.0-flash

    This neuron detects the news‐source and dateline markers that introduce article excerpts (e.g. outlet names, bracketed source tags, locations, publication 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
    _look
    -0.07
    oli
    -0.06
    ۲
    -0.06
    es
    -0.06
    ES
    -0.06
    -area
    -0.06
     still
    -0.06
    ğine
    -0.06
    ��
    -0.06
     предпол
    -0.05
    POSITIVE LOGITS
    ระบ
    0.08
     bog
    0.07
     grad
    0.07
    .ClientSize
    0.07
     stationary
    0.06
    (version
    0.06
     PLATFORM
    0.06
    Enable
    0.06
    perform
    0.06
     Dixon
    0.06
    Activations Density 0.027%

    No Known Activations