© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 128070
    Prev
    Next
    INDEX
    Explanations

    terms related to spoilers and warning alerts in narratives

    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
    ocos
    -0.06
     inst
    -0.06
    \Plugin
    -0.06
     çŃĶ
    -0.06
    929
    -0.06
    ist
    -0.06
     Inst
    -0.06
    wer
    -0.06
     Fond
    -0.06
    ãģ¨ãģ¯
    -0.06
    POSITIVE LOGITS
    ationale
    0.08
    umatic
    0.07
    ÄĽr
    0.07
    åģ¥
    0.07
    PerPixel
    0.07
    dsl
    0.06
    YLON
    0.06
    ein
    0.06
    gression
    0.06
    lda
    0.06
    Activations Density 0.003%

    No Known Activations