© 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. 130643
    Prev
    Next
    INDEX
    Explanations

    references to time and schedules

    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
    anth
    -0.07
     brunch
    -0.07
    íĴ
    -0.06
    нен
    -0.06
    onth
    -0.06
     hè
    -0.06
    scratch
    -0.06
    éré
    -0.06
     noon
    -0.06
    seau
    -0.06
    POSITIVE LOGITS
     late
    0.11
    late
    0.10
     Late
    0.10
     earliest
    0.09
     early
    0.09
    Late
    0.09
     Early
    0.08
     closing
    0.08
     finish
    0.08
     closed
    0.07
    Activations Density 0.025%

    No Known Activations