© 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. 15-LLAMASCOPE-RES-131K
    11. 61631
    Prev
    Next
    INDEX
    Explanations

    references to prominent figures or notable elements in a discussion

    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
    anie
    -0.07
    atoes
    -0.06
    rv
    -0.06
    aea
    -0.06
    anton
    -0.06
    arkan
    -0.06
     sque
    -0.06
    ANE
    -0.06
    amburger
    -0.06
    ево
    -0.06
    POSITIVE LOGITS
     mention
    0.09
     mentions
    0.08
     mentioned
    0.08
     Mention
    0.07
    mentioned
    0.07
     menc
    0.07
     examples
    0.07
     mentioning
    0.07
    mention
    0.07
    kker
    0.06
    Activations Density 0.013%

    No Known Activations