© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 126950
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific research and experimental methods

    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
    aru
    -0.06
    odo
    -0.06
    reon
    -0.06
     Holmes
    -0.06
    zt
    -0.06
     Thesis
    -0.06
    ail
    -0.06
    rouch
    -0.06
    ë
    -0.06
    ODO
    -0.06
    POSITIVE LOGITS
    omics
    0.07
    -deals
    0.07
    imas
    0.07
    odÄĽ
    0.07
    ÑĪиб
    0.07
     SPDX
    0.07
    jom
    0.07
     SetValue
    0.07
    εβ
    0.07
     nameof
    0.06
    Activations Density 0.000%

    No Known Activations