© 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. 130955
    Prev
    Next
    INDEX
    Explanations

    expressions of audience reactions and personal sentiments

    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
     maybe
    -0.07
     belki
    -0.07
    IfNeeded
    -0.07
     olabilir
    -0.07
     possibly
    -0.07
     dokonce
    -0.07
    maybe
    -0.06
     arguably
    -0.06
     perhaps
    -0.06
    squeeze
    -0.06
    POSITIVE LOGITS
    .sponge
    0.07
     pretty
    0.07
     Naturally
    0.07
     beaucoup
    0.07
     naturally
    0.06
    luent
    0.06
     neither
    0.06
     much
    0.06
    842
    0.06
    defgroup
    0.06
    Activations Density 0.016%

    No Known Activations