© 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. 106226
    Prev
    Next
    INDEX
    Explanations

    references to people and their roles

    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
    feld
    -0.07
    ilogy
    -0.06
    ories
    -0.06
    à¸ĵ
    -0.06
    owie
    -0.06
    ilo
    -0.06
    IFI
    -0.06
    ?action
    -0.06
    ilos
    -0.06
    (åľŁ
    -0.06
    POSITIVE LOGITS
     yourself
    0.07
    :
    0.07
     Mou
    0.06
    'll
    0.06
    836
    0.06
     ÎĶή
    0.06
    olley
    0.06
    ä¸įå®ī
    0.06
    oss
    0.06
    licken
    0.06
    Activations Density 0.013%

    No Known Activations