© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 71656
    Prev
    Next
    INDEX
    Explanations

    references to legal and regulatory documents

    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
     or
    -0.07
     its
    -0.07
    itz
    -0.07
    entina
    -0.06
     such
    -0.06
     that
    -0.06
    oric
    -0.06
    Bar
    -0.06
     in
    -0.06
     more
    -0.06
    POSITIVE LOGITS
     themselves
    0.10
     ê°ģê°ģ
    0.10
     obou
    0.09
    åĪĨåĪ«
    0.09
    ropol
    0.08
     thems
    0.08
     ëijĺ
    0.08
    defs
    0.08
    ê°ģ
    0.08
     smrt
    0.08
    Activations Density 0.099%

    No Known Activations