© 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. 40422
    Prev
    Next
    INDEX
    Explanations

    references to significant events or milestones

    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
    anz
    -0.07
    772
    -0.07
    aliz
    -0.07
    ulet
    -0.06
    424
    -0.06
    UMB
    -0.06
    ouz
    -0.06
     sport
    -0.06
     Strom
    -0.06
    .gg
    -0.06
    POSITIVE LOGITS
     versus
    0.10
     followed
    0.09
     vs
    0.08
    -vers
    0.08
    _vs
    0.08
     comple
    0.07
    vs
    0.07
    -vs
    0.07
    تص
    0.07
     ÙħÙĤابÙĦ
    0.07
    Activations Density 0.126%

    No Known Activations