© 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. 15-LLAMASCOPE-RES-131K
    11. 89720
    Prev
    Next
    INDEX
    Explanations

    structured data or identifiers related to programming or data processing

    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
     pik
    -0.09
    aylor
    -0.09
    acas
    -0.08
    usercontent
    -0.08
    -Requested
    -0.08
    ohan
    -0.08
    SupportedContent
    -0.07
    ога
    -0.07
    orsi
    -0.07
    ãĥĥãĤ«ãĥ¼
    -0.07
    POSITIVE LOGITS
     parent
    0.08
     fil
    0.07
     parents
    0.06
     profile
    0.06
     fin
    0.06
     underlying
    0.06
     source
    0.06
     master
    0.06
     associated
    0.06
     Tar
    0.06
    Activations Density 0.008%

    No Known Activations