© 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. 56362
    Prev
    Next
    INDEX
    Explanations

    terms related to digital marketing professionals and their credentials

    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
    oji
    -0.07
     steam
    -0.07
    uez
    -0.06
    parate
    -0.06
     mil
    -0.06
    steam
    -0.06
     ballo
    -0.06
     blo
    -0.06
    ogany
    -0.06
    _blob
    -0.06
    POSITIVE LOGITS
    èĺ
    0.07
     zd
    0.07
    aklı
    0.07
     industry
    0.07
    itre
    0.06
     Columns
    0.06
    industry
    0.06
     evangel
    0.06
    Äįer
    0.06
     tablesp
    0.06
    Activations Density 0.006%

    No Known Activations