© 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. 9-LLAMASCOPE-RES-131K
    11. 95370
    Prev
    Next
    INDEX
    Explanations

    references to mathematical domains and sets

    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
    ker
    -0.07
    OrDefault
    -0.07
    ita
    -0.06
    ston
    -0.06
    hta
    -0.06
     lif
    -0.06
     trace
    -0.06
    uen
    -0.06
     turn
    -0.06
    itag
    -0.05
    POSITIVE LOGITS
    oins
    0.09
    chet
    0.08
     Fav
    0.07
    ÄĽr
    0.07
    ypi
    0.07
    /Area
    0.07
    afone
    0.07
    amble
    0.07
    å®Ļ
    0.07
    léd
    0.07
    Activations Density 0.068%

    No Known Activations