© 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. 75657
    Prev
    Next
    INDEX
    Explanations

    occurrences and references to past events and conditions

    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
    ilton
    -0.06
    yper
    -0.06
    atti
    -0.06
    jug
    -0.06
    æİĪ
    -0.06
    insk
    -0.06
    icerca
    -0.06
    ãģŀ
    -0.06
    ogl
    -0.06
    ogie
    -0.06
    POSITIVE LOGITS
    afka
    0.07
     throughout
    0.07
    anje
    0.07
    869
    0.07
     elsewhere
    0.07
    麻
    0.06
     Throughout
    0.06
    ãĥ³ãĥĨãĤ£
    0.06
    838
    0.06
    bish
    0.06
    Activations Density 0.015%

    No Known Activations