© 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. 16797
    Prev
    Next
    INDEX
    Explanations

    references to academic programs and training opportunities

    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
    undle
    -0.08
    ignum
    -0.07
    enet
    -0.07
    ierce
    -0.06
    hta
    -0.06
    erglass
    -0.06
    tah
    -0.06
    ilm
    -0.06
    cea
    -0.06
    enville
    -0.06
    POSITIVE LOGITS
    ModelProperty
    0.08
    ÑĤÑĢон
    0.07
     Intr
    0.07
     investigator
    0.07
    .nih
    0.07
    arhus
    0.07
    RTC
    0.06
     Blast
    0.06
    ueva
    0.06
     careers
    0.06
    Activations Density 0.030%

    No Known Activations