© 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. 15-LLAMASCOPE-RES-131K
    11. 61269
    Prev
    Next
    INDEX
    Explanations

    references to educational programs and awards related to students and literature

    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
    ammen
    -0.07
    ĨĴ
    -0.07
     Criterion
    -0.06
    озна
    -0.06
    aise
    -0.06
    alse
    -0.06
    rente
    -0.06
    ÅĻet
    -0.06
     Humanities
    -0.06
    inent
    -0.05
    POSITIVE LOGITS
     separate
    0.12
     separately
    0.11
     Separate
    0.11
     seperate
    0.11
     ebenfalls
    0.09
     similarly
    0.09
     equally
    0.09
     оÑĤделÑĮ
    0.09
    Separ
    0.09
     ÑĤоже
    0.08
    Activations Density 0.039%

    No Known Activations