© 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. 17-LLAMASCOPE-RES-131K
    11. 60123
    Prev
    Next
    INDEX
    Explanations

    elements related to scientific and historical analysis

    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
    ÃŃr
    -0.07
    itung
    -0.07
    orgh
    -0.07
    meld
    -0.06
    Ñĥла
    -0.06
    akah
    -0.06
    ùng
    -0.06
    elow
    -0.06
    è¯
    -0.06
    olor
    -0.06
    POSITIVE LOGITS
     examples
    0.09
     personal
    0.08
     example
    0.08
     historical
    0.07
     relevant
    0.07
     Examples
    0.07
     case
    0.07
    /examples
    0.07
    tit
    0.07
    esk
    0.07
    Activations Density 0.021%

    No Known Activations