© 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. 77758
    Prev
    Next
    INDEX
    Explanations

    terms related to various functions or roles in professional settings

    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
     etc
    -0.11
     instead
    -0.09
     and
    -0.08
    etc
    -0.08
     or
    -0.07
     Vs
    -0.07
     alone
    -0.07
     Instead
    -0.07
     vs
    -0.07
    -ÑĤо
    -0.07
    POSITIVE LOGITS
     alike
    0.18
     olmak
    0.11
     Äijá»ģu
    0.10
     equally
    0.09
    rous
    0.08
    æĸ¹éĿ¢
    0.08
    depending
    0.08
     sides
    0.08
     aspects
    0.07
     depending
    0.07
    Activations Density 0.041%

    No Known Activations