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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 119252
    Prev
    Next
    INDEX
    Explanations

    mentions of specific chemical elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onto
    -0.07
    yal
    -0.07
    zac
    -0.07
    /high
    -0.07
    idth
    -0.07
    گرد
    -0.07
    braco
    -0.07
    ós
    -0.07
    abbix
    -0.07
    ÃŃna
    -0.06
    POSITIVE LOGITS
    ingt
    0.08
    ing
    0.07
    ìĭ
    0.07
    tsky
    0.06
    Ļ
    0.06
     plants
    0.06
    $rows
    0.06
    ÂŃing
    0.06
    _pp
    0.06
    cÃŃ
    0.06
    Activations Density 0.001%

    No Known Activations