© 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. 125087
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to electrical engineering and amplifiers

    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
    wig
    -0.07
    -wow
    -0.07
    /container
    -0.07
    sik
    -0.06
     encyclopedia
    -0.06
    ija
    -0.06
    thur
    -0.06
    overy
    -0.06
     Till
    -0.06
    /cpp
    -0.06
    POSITIVE LOGITS
     supply
    0.07
    è¯Ŀ
    0.07
     ÑģÑħем
    0.06
    _DEAD
    0.06
    erez
    0.06
    AGED
    0.06
    .parameter
    0.06
    adies
    0.06
    jsc
    0.06
    edback
    0.06
    Activations Density 0.029%

    No Known Activations