© 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. 4225
    Prev
    Next
    INDEX
    Explanations

    terms related to boxing tactics and match analysis

    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
    trag
    -0.07
    zzle
    -0.07
    Pitch
    -0.07
    quential
    -0.06
     rast
    -0.06
     kvin
    -0.06
    ä»
    -0.06
    ãĤ±ãĥĥãĥĪ
    -0.06
    ipples
    -0.06
    ewitness
    -0.06
    POSITIVE LOGITS
    ór
    0.07
    expo
    0.06
    utilus
    0.06
     technique
    0.06
    íĺķ
    0.06
    ohon
    0.06
    çĴ°
    0.06
     conserv
    0.06
    aware
    0.06
    chin
    0.06
    Activations Density 0.004%

    No Known Activations