© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 22-LLAMASCOPE-RES-131K
    11. 4099
    Prev
    Next
    INDEX
    Explanations

    specific types of signage and visual elements related to branding and icons

    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
    .scalablytyped
    -0.08
    GuidId
    -0.08
    omo
    -0.07
    statt
    -0.07
     IOCTL
    -0.07
    _Tis
    -0.07
    shint
    -0.07
    ëį°ìĿ´íĬ¸
    -0.07
    CallCheck
    -0.06
    åĦĢ
    -0.06
    POSITIVE LOGITS
     neon
    0.13
     letters
    0.11
     Neon
    0.11
     Letters
    0.10
     letter
    0.09
    Letters
    0.09
     lights
    0.09
    letters
    0.09
     LED
    0.08
     Letter
    0.08
    Activations Density 0.003%

    No Known Activations