© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 56001
    Prev
    Next
    INDEX
    Explanations

    details about healthcare plans and procedures

    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
    rees
    -0.06
    ingers
    -0.06
    upd
    -0.06
     Annunci
    -0.06
    plex
    -0.06
    287
    -0.06
     Knock
    -0.06
    Specifier
    -0.06
    976
    -0.06
    å¼ı
    -0.06
    POSITIVE LOGITS
    à¹Ģà¸Ĺ
    0.07
     cunt
    0.07
    fre
    0.07
    antium
    0.06
    dad
    0.06
     evacuated
    0.06
    holm
    0.06
     iddi
    0.06
     lace
    0.06
    efa
    0.06
    Activations Density 0.002%

    No Known Activations