© 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. 82484
    Prev
    Next
    INDEX
    Explanations

    elements related to environment, atmosphere, and social interactions

    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
    é¼»
    -0.07
    AZY
    -0.06
    .obs
    -0.06
    alsy
    -0.06
    azy
    -0.06
     Corpus
    -0.06
    POSIT
    -0.06
    ìį¨
    -0.06
    upos
    -0.06
    inters
    -0.06
    POSITIVE LOGITS
    ÑĨей
    0.07
     Böl
    0.06
    ripple
    0.06
    ế
    0.06
    ril
    0.06
     Dollars
    0.06
    picker
    0.06
    té
    0.06
    elman
    0.06
    thouse
    0.06
    Activations Density 0.001%

    No Known Activations