© 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. 82789
    Prev
    Next
    INDEX
    Explanations

    references to various qualities and characteristics associated with materials, processes, and relationships

    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
    gal
    -0.06
    rk
    -0.06
    bla
    -0.06
    iferay
    -0.06
    ãģ¨ãģĨ
    -0.06
     pencil
    -0.05
    ære
    -0.05
    ils
    -0.05
    691
    -0.05
     âĹĦ
    -0.05
    POSITIVE LOGITS
    วย
    0.08
    NEXT
    0.08
    longleftrightarrow
    0.07
     Characters
    0.07
    ubber
    0.07
    IRD
    0.06
    /GPL
    0.06
    .twig
    0.06
    uplicate
    0.06
    orate
    0.06
    Activations Density 0.050%

    No Known Activations