© 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. 126622
    Prev
    Next
    INDEX
    Explanations

    dates and numerical information

    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
     (
    -0.06
     v
    -0.06
    æĿī
    -0.06
    ourt
    -0.05
     w
    -0.05
    åde
    -0.05
    itsu
    -0.05
    argent
    -0.05
     Poison
    -0.05
    sel
    -0.05
    POSITIVE LOGITS
    imli
    0.08
    vÃŃc
    0.07
    utenberg
    0.07
    æĥ
    0.07
     tiener
    0.07
    ÑıÑĤелÑĮ
    0.07
     Raq
    0.07
    biên
    0.07
    λαν
    0.07
     OMIT
    0.07
    Activations Density 0.044%

    No Known Activations