© 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. 76212
    Prev
    Next
    INDEX
    Explanations

    concepts related to relationships and abstract philosophical ideas

    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
    ä»Ĭå¹´
    -0.07
    recent
    -0.06
     lately
    -0.06
    -м
    -0.06
     recently
    -0.06
    à¸ģำล
    -0.06
     Faster
    -0.06
     kür
    -0.06
     newest
    -0.06
    POSITIVE LOGITS
    venida
    0.07
    ividual
    0.07
    igli
    0.06
    ycastle
    0.06
    burgh
    0.06
    iginal
    0.06
    igua
    0.06
    arella
    0.06
    ør
    0.06
     motivational
    0.06
    Activations Density 0.003%

    No Known Activations