© 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. 84604
    Prev
    Next
    INDEX
    Explanations

    terms related to educational or regulatory contexts, particularly focusing on standards and assessments

    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
    ÑģÑĮ
    -0.07
    ided
    -0.07
    emachine
    -0.07
    otu
    -0.07
    oksen
    -0.07
     Vander
    -0.07
    loo
    -0.06
    ìĽIJìĿ´
    -0.06
    #ad
    -0.06
    ltk
    -0.06
    POSITIVE LOGITS
    _HERSHEY
    0.06
    heiro
    0.06
    edia
    0.06
    olia
    0.06
    fig
    0.06
    ateria
    0.06
    èĤ©
    0.06
    ApplicationBuilder
    0.06
    attery
    0.06
    áf
    0.06
    Activations Density 0.125%

    No Known Activations