© 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 EvalsExportsinterp-engineNEWAPI 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. 70315
    Prev
    Next
    INDEX
    Explanations

    expressions of excitement and anticipation

    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
     eventual
    -0.06
    erto
    -0.06
    191
    -0.06
     frustration
    -0.06
    382
    -0.06
    追
    -0.06
    ory
    -0.06
     intersection
    -0.06
    ä½ĵ
    -0.06
    rt
    -0.06
    POSITIVE LOGITS
     exciting
    0.10
     nervous
    0.10
     excitement
    0.09
     excited
    0.09
     preparations
    0.08
    heimer
    0.08
    ekli
    0.07
    ãĥ³ãĥĸ
    0.07
     adventure
    0.07
    _prep
    0.07
    Activations Density 0.024%

    No Known Activations