© 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. 127108
    Prev
    Next
    INDEX
    Explanations

    HTML elements and components related to website navigation

    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
    åĿ¦
    -0.07
    assi
    -0.07
    _rpc
    -0.06
    ãĥĥãĥĪ
    -0.06
    é»ĺ
    -0.06
     pai
    -0.06
     premier
    -0.06
    esium
    -0.06
     RPC
    -0.06
     meno
    -0.05
    POSITIVE LOGITS
    CHAT
    0.07
    ëĭ
    0.07
    'gc
    0.07
    sonian
    0.07
     span
    0.06
    lash
    0.06
    GIN
    0.06
    .ResponseWriter
    0.06
    祥
    0.06
    å·§
    0.06
    Activations Density 0.003%

    No Known Activations