© 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. 82238
    Prev
    Next
    INDEX
    Explanations

    references to visiting websites or locations

    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
    оло
    -0.07
     Followers
    -0.07
    pic
    -0.07
    olo
    -0.07
    arena
    -0.07
    StandardItem
    -0.07
    reach
    -0.06
    ets
    -0.06
    _WS
    -0.06
    WS
    -0.06
    POSITIVE LOGITS
     www
    0.10
     http
    0.10
     https
    0.10
    www
    0.09
    ä¸Ģä¸ĭ
    0.07
    _https
    0.07
    https
    0.07
    gota
    0.07
     our
    0.07
    http
    0.07
    Activations Density 0.008%

    No Known Activations