© 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. 106373
    Prev
    Next
    INDEX
    Explanations

    terms related to compliance, performance, and technological advancements in a business context

    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
    endor
    -0.06
     Micha
    -0.06
    oric
    -0.06
    ceae
    -0.06
     Sticky
    -0.06
    ork
    -0.06
    IFA
    -0.06
     müdür
    -0.06
    exion
    -0.06
    ráž
    -0.06
    POSITIVE LOGITS
     Zam
    0.07
    oller
    0.06
    uten
    0.06
    erald
    0.06
    ãĥĢãĤ¤
    0.06
    urgeon
    0.06
    Automation
    0.06
    izyon
    0.06
     dialogue
    0.06
    lando
    0.06
    Activations Density 0.034%

    No Known Activations