© 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. 16921
    Prev
    Next
    INDEX
    Explanations

    technical terms and processes related to audio technology and signal processing

    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
     einer
    -0.08
     prob
    -0.07
    someone
    -0.07
    برÛĮ
    -0.07
     einem
    -0.07
    amp
    -0.06
    nbsp
    -0.06
    вин
    -0.06
    ensex
    -0.06
     someone
    -0.06
    POSITIVE LOGITS
     the
    0.16
    ,the
    0.12
    	the
    0.12
    _the
    0.10
    the
    0.10
    /the
    0.09
    .the
    0.09
    _both
    0.08
     The
    0.08
    	The
    0.08
    Activations Density 0.753%

    No Known Activations