© 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. 17-LLAMASCOPE-RES-131K
    11. 93974
    Prev
    Next
    INDEX
    Explanations

    references to other class definitions or documentation links in a programming context

    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
    anza
    -0.07
    erb
    -0.07
    obb
    -0.07
    ignum
    -0.07
    baum
    -0.06
    _FRAMEBUFFER
    -0.06
    erti
    -0.06
    uce
    -0.06
    ignet
    -0.06
    oled
    -0.06
    POSITIVE LOGITS
    panion
    0.07
    ¯
    0.06
     Bowling
    0.06
    atsapp
    0.06
    agli
    0.06
    /Core
    0.06
    ãĤ¹ãĤ¯
    0.06
     sealing
    0.06
    æĥħ
    0.06
     Zucker
    0.06
    Activations Density 0.002%

    No Known Activations