© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 91205
    Prev
    Next
    INDEX
    Explanations

    interaction

    np_max-act · gemini-2.0-flash

    scientific terminology related to cosmic phenomena, specifically focused on galaxies and their properties.

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

    This neuron fires on terms describing shock‐ and merger‐related phenomena in galaxy clusters (e.g. radio relics, shocks, merging clusters).

    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
     Madness
    -0.07
    thur
    -0.06
     european
    -0.06
     spells
    -0.06
     Erotische
    -0.06
     muttered
    -0.06
     fair
    -0.06
     ruled
    -0.06
     Guru
    -0.06
    י�
    -0.06
    POSITIVE LOGITS
     Người
    0.06
     görüntü
    0.06
    ，您
    0.06
    หย
    0.06
    _CURRENT
    0.06
    iệu
    0.06
     comparatively
    0.06
     Рег
    0.06
    ็ม
    0.06
     การ
    0.06
    Activations Density 0.007%

    No Known Activations