© 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. 128381
    Prev
    Next
    INDEX
    Explanations

    statistics and percentages related to access to essential resources

    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
    lak
    -0.06
    usch
    -0.06
    udeau
    -0.06
    å°±æĺ¯
    -0.06
    à¹Īà¸Ńม
    -0.06
    ÙĤب
    -0.06
    nge
    -0.06
     Soon
    -0.06
    ieg
    -0.06
    zan
    -0.06
    POSITIVE LOGITS
     ever
    0.09
    277
    0.08
    羣æŃ£
    0.08
     actually
    0.08
     fully
    0.08
     truly
    0.07
     Fully
    0.07
     nÃło
    0.07
     actual
    0.06
    andalone
    0.06
    Activations Density 0.017%

    No Known Activations