© 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. 83338
    Prev
    Next
    INDEX
    Explanations

    references to the Husky breed of dogs

    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
    zes
    -0.08
    zers
    -0.07
    itter
    -0.07
    _PF
    -0.06
    tte
    -0.06
    ANGE
    -0.06
    ós
    -0.06
    itzer
    -0.06
    ήÏĤ
    -0.06
    resher
    -0.06
    POSITIVE LOGITS
    afia
    0.07
    elage
    0.07
    erli
    0.07
    áng
    0.07
    oldt
    0.06
    izzo
    0.06
    ÑĸйÑģÑĮкоÑĹ
    0.06
    peria
    0.06
    ereal
    0.06
    fection
    0.06
    Activations Density 0.007%

    No Known Activations