© 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. 127246
    Prev
    Next
    INDEX
    Explanations

    instances of numerical values associated with significance or emphasis

    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
    оза
    -0.07
     aras
    -0.07
    utherford
    -0.07
    urb
    -0.06
    ardon
    -0.06
    lect
    -0.06
    actory
    -0.06
     Telegraph
    -0.06
    quirrel
    -0.06
     strongly
    -0.06
    POSITIVE LOGITS
     Tactics
    0.07
    ebi
    0.07
    robat
    0.07
    íĥĦ
    0.06
    FixedSize
    0.06
     thoughts
    0.06
    antz
    0.06
    ffd
    0.06
    ernes
    0.06
    isure
    0.06
    Activations Density 0.002%

    No Known Activations