© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 89231
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols and their contextual use in technical settings

    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
     SKF
    -0.07
    iÄįka
    -0.07
    _MSK
    -0.06
    dana
    -0.06
    RLF
    -0.06
    imin
    -0.06
    ovo
    -0.06
    еÑĤÑĮ
    -0.06
     Mirage
    -0.06
    ữa
    -0.06
    POSITIVE LOGITS
    ifen
    0.07
    /topics
    0.06
    agon
    0.06
    ]){
    0.06
    ilon
    0.06
    ag
    0.06
    iasm
    0.06
    /moment
    0.06
    osaur
    0.06
    irit
    0.06
    Activations Density 0.000%

    No Known Activations