© 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. 3788
    Prev
    Next
    INDEX
    Explanations

    phrases indicating updates or new information

    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
    itet
    -0.06
    utschein
    -0.06
     both
    -0.06
    äh
    -0.06
    666
    -0.06
    adu
    -0.06
     least
    -0.05
    orp
    -0.05
    wick
    -0.05
     rất
    -0.05
    POSITIVE LOGITS
    mere
    0.15
     merely
    0.14
     mere
    0.13
    isol
    0.10
     simplement
    0.10
     nor
    0.10
     anymore
    0.08
     isolated
    0.08
    åıªæĺ¯
    0.08
     necessarily
    0.08
    Activations Density 0.037%

    No Known Activations