© 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. 83188
    Prev
    Next
    INDEX
    Explanations

    terms related to baseball statistics and actions

    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
    коÑĤ
    -0.07
    lrt
    -0.07
    lej
    -0.07
    nock
    -0.07
    unma
    -0.07
    indow
    -0.07
    æīĢå±ŀ
    -0.07
    abric
    -0.07
    podob
    -0.07
    snap
    -0.07
    POSITIVE LOGITS
    iÄįe
    0.06
    à¥Įन
    0.06
    oste
    0.06
     opportun
    0.06
     wor
    0.05
    etta
    0.05
     non
    0.05
     gloss
    0.05
     zoning
    0.05
    avn
    0.05
    Activations Density 0.001%

    No Known Activations