© 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. 119055
    Prev
    Next
    INDEX
    Explanations

    references to international agreements and climate change discussions

    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
     McCabe
    -0.07
     nationwide
    -0.06
    udos
    -0.06
    สำ
    -0.06
    inema
    -0.06
     IMPLIED
    -0.06
    ibal
    -0.06
    ãĤ·ãĤ¢
    -0.06
    anggal
    -0.06
     gratuitement
    -0.06
    POSITIVE LOGITS
     summit
    0.11
    å³°
    0.10
     Summit
    0.09
    odash
    0.08
    plen
    0.08
     meetings
    0.07
    Injector
    0.07
     conference
    0.07
     meeting
    0.07
    Sum
    0.07
    Activations Density 0.057%

    No Known Activations