© 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. 83416
    Prev
    Next
    INDEX
    Explanations

    phrases indicating purpose or benefit

    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
    quette
    -0.10
    awy
    -0.07
    üler
    -0.06
    223
    -0.06
    ẩm
    -0.06
    yon
    -0.06
    vents
    -0.06
    ala
    -0.06
     Regards
    -0.06
    ALLERY
    -0.06
    POSITIVE LOGITS
    bidden
    0.07
     sale
    0.07
     ActiveForm
    0.07
    nah
    0.07
    cast
    0.07
    aken
    0.06
    ighted
    0.06
     SALE
    0.06
    ãĥ³ãĥģ
    0.06
    Å¡ov
    0.06
    Activations Density 0.010%

    No Known Activations