© 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. 118573
    Prev
    Next
    INDEX
    Explanations

    instructions related to cooking processes

    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
    rosso
    -0.07
    blk
    -0.07
    levation
    -0.06
    ivr
    -0.06
    .xyz
    -0.06
     Jewel
    -0.06
     Marina
    -0.06
    ãĥĥãĥĦ
    -0.06
    ashion
    -0.06
    bjerg
    -0.06
    POSITIVE LOGITS
     aggreg
    0.07
    ]={↵
    0.07
     Granite
    0.06
    ãĤ¹ãĤ¯
    0.06
     adjud
    0.06
    annah
    0.06
    argon
    0.06
    uber
    0.06
     Nez
    0.06
    verter
    0.06
    Activations Density 0.006%

    No Known Activations