© 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. 3710
    Prev
    Next
    INDEX
    Explanations

    references to academic citations and sources within a scientific 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
    Ñģим
    -0.07
    imetype
    -0.07
    ĴĪ
    -0.07
    ök
    -0.07
    cery
    -0.06
    openh
    -0.06
    orbit
    -0.06
    ìļ´ëį°
    -0.06
    iscopal
    -0.06
    etty
    -0.06
    POSITIVE LOGITS
    201
    0.09
    200
    0.08
    /goto
    0.07
    199
    0.06
    UGIN
    0.06
    æª
    0.06
     addCriterion
    0.06
     undermined
    0.06
     et
    0.06
    08
    0.06
    Activations Density 0.012%

    No Known Activations