© 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. 85607
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or actions related to data or research outputs

    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
    owie
    -0.08
    asl
    -0.07
    ingroup
    -0.07
    ISP
    -0.07
    ãģĤ
    -0.07
    ystack
    -0.07
    ongan
    -0.06
    umd
    -0.06
    etwork
    -0.06
    شتÙĩ
    -0.06
    POSITIVE LOGITS
    üç
    0.07
     Sweat
    0.07
    ic
    0.07
    aldo
    0.06
    uc
    0.06
    kle
    0.06
    assi
    0.06
    ac
    0.06
     stim
    0.06
     recreation
    0.06
    Activations Density 0.003%

    No Known Activations