© 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. 15-LLAMASCOPE-RES-131K
    11. 88313
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and definitions in a formal context

    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
    orts
    -0.07
    stype
    -0.07
    ies
    -0.06
    wind
    -0.06
    ija
    -0.06
    ysz
    -0.06
    exus
    -0.06
    tej
    -0.06
    ä¸įæĺ¯
    -0.06
    azel
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.06
    ender
    0.06
    oreach
    0.06
    .sock
    0.06
    eva
    0.06
     escorts
    0.06
    Ñij
    0.06
    راÙģ
    0.06
     Scho
    0.06
    ArrayType
    0.06
    Activations Density 0.107%

    No Known Activations