© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 39888
    Prev
    Next
    INDEX
    Explanations

    keywords related to special education and support services

    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
    enie
    -0.07
    enant
    -0.07
     Saturn
    -0.06
    INST
    -0.06
    Combo
    -0.06
    angstrom
    -0.06
    ä¸Ī
    -0.06
     Jennings
    -0.06
     Buen
    -0.06
    ì²´
    -0.06
    POSITIVE LOGITS
     mainstream
    0.08
     Special
    0.08
    Special
    0.07
     disability
    0.07
     accommod
    0.07
    rame
    0.07
     SPECIAL
    0.07
    icap
    0.07
    ç®Ĭ
    0.07
     special
    0.07
    Activations Density 0.019%

    No Known Activations