© 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. 15-LLAMASCOPE-RES-131K
    11. 62228
    Prev
    Next
    INDEX
    Explanations

    references to health care policies and funding proposals

    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
    ificio
    -0.07
    upo
    -0.07
    iVar
    -0.07
     voks
    -0.07
    gne
    -0.07
    stk
    -0.06
    £¨
    -0.06
    å»Ĭ
    -0.06
     Goldberg
    -0.06
    arse
    -0.06
    POSITIVE LOGITS
     Leader
    0.07
    ysi
    0.06
    entials
    0.06
    oley
    0.06
     Whip
    0.06
     Ve
    0.06
    ropy
    0.06
    _Util
    0.06
    ve
    0.06
     promise
    0.06
    Activations Density 0.020%

    No Known Activations