© 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. 128199
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and electronics industries

    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
    .dep
    -0.07
    znik
    -0.07
    ponge
    -0.07
    nze
    -0.07
    rud
    -0.07
    aç
    -0.07
    KeySpec
    -0.07
    eview
    -0.06
    ãĥ¼ãĤ¸
    -0.06
    loor
    -0.06
    POSITIVE LOGITS
     player
    0.08
     major
    0.08
     vendor
    0.08
     vendors
    0.08
     majors
    0.08
     giants
    0.07
     companies
    0.07
     industry
    0.07
     supplier
    0.07
    player
    0.07
    Activations Density 0.031%

    No Known Activations