© 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. 40485
    Prev
    Next
    INDEX
    Explanations

    concepts related to lifestyle and creative expression

    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
     but
    -0.09
     deÄŁil
    -0.08
     rather
    -0.08
    ãģ§ãģ¯ãģªãģı
    -0.08
    ãģ¨ãģ¯
    -0.07
     compared
    -0.07
    以å¤ĸ
    -0.07
    but
    -0.07
     Vs
    -0.07
    ï¼Įä½Ĩ
    -0.07
    POSITIVE LOGITS
     ones
    0.07
    ailability
    0.06
    ãģ®æĸ¹
    0.06
     itself
    0.06
    igest
    0.06
    opot
    0.06
    ÄĻk
    0.06
     altogether
    0.06
    rv
    0.05
    igration
    0.05
    Activations Density 0.074%

    No Known Activations