© 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. 118465
    Prev
    Next
    INDEX
    Explanations

    references to medical databases and sources

    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
     asset
    -0.07
     Brennan
    -0.06
    assen
    -0.06
     Asset
    -0.06
     Tea
    -0.06
    rido
    -0.06
     racing
    -0.06
    asset
    -0.06
    çģ
    -0.05
     Emerson
    -0.05
    POSITIVE LOGITS
    .nlm
    0.13
    .nih
    0.09
     Bethesda
    0.08
    AMED
    0.08
    .gov
    0.07
    .ncbi
    0.07
    सर
    0.07
    ÑģÑıг
    0.07
    úsqueda
    0.07
     abstract
    0.07
    Activations Density 0.016%

    No Known Activations