© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 90861
    Prev
    Next
    INDEX
    Explanations

    technical references related to automotive engineering and performance

    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
    важ
    -0.07
    .TryParse
    -0.07
     wol
    -0.07
    åij³
    -0.07
    Destructor
    -0.06
    .quality
    -0.06
    à¤ĺ
    -0.06
    iesel
    -0.06
    аÑģÑĤ
    -0.06
    fell
    -0.06
    POSITIVE LOGITS
     design
    0.07
    ayne
    0.06
     team
    0.06
    Sortable
    0.06
    exo
    0.06
     bÃŃ
    0.06
    eyer
    0.06
    erus
    0.06
    utter
    0.06
    üp
    0.06
    Activations Density 0.003%

    No Known Activations