© 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. 87158
    Prev
    Next
    INDEX
    Explanations

    mentions of podcasts and audio content

    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
    наÑĢÑĥж
    -0.06
    нед
    -0.06
    acio
    -0.06
    rint
    -0.06
    à¸Ĭร
    -0.06
    _DEF
    -0.06
    _cf
    -0.06
     threadIdx
    -0.06
    çĪµ
    -0.06
     ä¿Ŀ
    -0.06
    POSITIVE LOGITS
    AndView
    0.07
     content
    0.07
    Chunks
    0.06
    imony
    0.06
    caught
    0.06
    TestFixture
    0.06
    Pocket
    0.06
    ushima
    0.06
    licit
    0.06
     entertainment
    0.06
    Activations Density 0.007%

    No Known Activations