© 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. 40990
    Prev
    Next
    INDEX
    Explanations

    references to sections and results in a report or 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
    Æ°Æ¡ng
    -0.07
    ustos
    -0.07
    ynom
    -0.06
    ityEngine
    -0.06
    γκα
    -0.06
    CHA
    -0.06
    incy
    -0.06
    acad
    -0.06
    SystemService
    -0.06
    adaki
    -0.06
    POSITIVE LOGITS
     results
    0.17
     Results
    0.15
    results
    0.14
    Results
    0.13
     RESULTS
    0.13
    _results
    0.13
    -results
    0.13
    RESULTS
    0.12
    _RESULTS
    0.11
    .results
    0.11
    Activations Density 0.082%

    No Known Activations