© 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. 119700
    Prev
    Next
    INDEX
    Explanations

    terms related to nominations and references for awards

    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
    ifestyles
    -0.09
    zas
    -0.08
    nila
    -0.08
    hos
    -0.07
    Ð¡Ðł
    -0.07
    ẫn
    -0.07
    ãģĴ
    -0.07
    .MixedReality
    -0.07
    ĮĢ
    -0.07
    ingo
    -0.07
    POSITIVE LOGITS
     witness
    0.07
     recent
    0.07
     Witness
    0.06
     current
    0.06
    973
    0.06
     currentItem
    0.06
     witnessed
    0.06
     former
    0.06
     past
    0.06
    720
    0.05
    Activations Density 0.004%

    No Known Activations