© 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. 70818
    Prev
    Next
    INDEX
    Explanations

    keywords and metadata in technical or formal 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
    sWith
    -0.07
    unkt
    -0.07
    rello
    -0.07
    zÃŃ
    -0.07
    UBL
    -0.07
    oct
    -0.06
     zaj
    -0.06
    à¹ĭ
    -0.06
    ëªħ
    -0.06
    abella
    -0.06
    POSITIVE LOGITS
    βολ
    0.07
    pong
    0.06
    meer
    0.06
    lett
    0.06
     keywords
    0.06
     Dean
    0.06
    itt
    0.06
    keywords
    0.06
    ÙĬÙĨÙĩ
    0.06
     Keywords
    0.06
    Activations Density 0.001%

    No Known Activations