© 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. 106380
    Prev
    Next
    INDEX
    Explanations

    references to a specific website and expressions of gratitude

    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
     (
    -0.08
     ..
    -0.07
     ...
    -0.07
     ("
    -0.06
     thread
    -0.06
     uncon
    -0.06
     stake
    -0.06
     —
    -0.06
     "
    -0.06
     pile
    -0.06
    POSITIVE LOGITS
     kancel
    0.08
    eland
    0.08
    catid
    0.07
    ebek
    0.07
    holm
    0.07
     lesb
    0.07
    edd
    0.07
    ç´°
    0.07
    .documentation
    0.07
    strup
    0.07
    Activations Density 0.000%

    No Known Activations