© 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. 3088
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to scientific and engineering contexts

    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
     Contributor
    -0.07
     æĤ
    -0.07
    iton
    -0.07
    бин
    -0.06
    æŃ©
    -0.06
     åħ±
    -0.06
    chant
    -0.06
    ãĤ¼
    -0.06
    онд
    -0.06
     aside
    -0.06
    POSITIVE LOGITS
     between
    0.09
    between
    0.08
     giữa
    0.08
     междÑĥ
    0.07
     zwischen
    0.07
     addCriterion
    0.07
    ouser
    0.07
     BETWEEN
    0.07
     involving
    0.07
     vice
    0.07
    Activations Density 0.063%

    No Known Activations