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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 104996
    Prev
    Next
    INDEX
    Explanations

    mentions of carbon-based materials and their applications

    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
    hape
    -0.06
    bau
    -0.06
    extensions
    -0.06
     fluoride
    -0.06
    MY
    -0.06
     abol
    -0.06
    ãĥ¼ãĤ¸
    -0.06
    clip
    -0.06
     extensions
    -0.05
     Graz
    -0.05
    POSITIVE LOGITS
     com
    0.08
    層
    0.07
     Suspension
    0.07
     suspension
    0.07
    _Matrix
    0.07
    еком
    0.07
    embedding
    0.07
     filler
    0.07
    Susp
    0.06
     Associ
    0.06
    Activations Density 0.035%

    No Known Activations