© 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. 125468
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers or metadata associated with publication details

    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
    @nate
    -0.08
    ä¸ĺ
    -0.07
    altung
    -0.07
     Dexter
    -0.07
    á»±
    -0.07
     ëĭµ
    -0.06
     bạc
    -0.06
    pivot
    -0.06
    /gtest
    -0.06
     Soros
    -0.06
    POSITIVE LOGITS
    olk
    0.06
    oad
    0.06
     chapters
    0.05
    Chapter
    0.05
     CHAPTER
    0.05
     patt
    0.05
    bil
    0.05
     provision
    0.05
    anko
    0.05
    ardi
    0.05
    Activations Density 0.004%

    No Known Activations