© 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 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. 59359
    Prev
    Next
    INDEX
    Explanations

    concepts of interconnectedness and relationships between entities or ideas

    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
    жив
    -0.08
    ardi
    -0.07
    æľĭ
    -0.07
    kok
    -0.07
    /people
    -0.07
    odor
    -0.07
    à¹Ĥà¸Ĺ
    -0.07
    BITS
    -0.07
    anton
    -0.07
    vang
    -0.07
    POSITIVE LOGITS
     with
    0.08
    sWith
    0.07
    tures
    0.07
    essen
    0.07
    /out
    0.06
     cul
    0.06
    ĶåĽŀ
    0.06
     tighter
    0.06
     webs
    0.06
     throughout
    0.06
    Activations Density 0.010%

    No Known Activations