© 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. 75266
    Prev
    Next
    INDEX
    Explanations

    information related to events and their scheduling

    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
    å½
    -0.08
     Rip
    -0.07
    alar
    -0.07
    æĬľ
    -0.07
    ă
    -0.07
    igor
    -0.07
    jal
    -0.06
    ernen
    -0.06
     Tribal
    -0.06
    Defense
    -0.06
    POSITIVE LOGITS
     Caribbean
    0.08
     Trinidad
    0.07
     Bahamas
    0.07
     Persons
    0.07
     GPL
    0.07
     persons
    0.07
     Dias
    0.07
     Belize
    0.07
     island
    0.07
     Georgetown
    0.07
    Activations Density 0.106%

    No Known Activations