© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 83311
    Prev
    Next
    INDEX
    Explanations

    references to specific missions or objectives

    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
    idence
    -0.06
    ask
    -0.06
    342
    -0.06
    ãĥĨãĥ«
    -0.06
    ça
    -0.06
     Ấ
    -0.06
    ilk
    -0.05
    ICI
    -0.05
    ì§Ī
    -0.05
     Pou
    -0.05
    POSITIVE LOGITS
    naire
    0.12
    aries
    0.11
    naires
    0.11
    ary
    0.11
    ellt
    0.10
    aira
    0.08
    arie
    0.08
    帯
    0.08
    aires
    0.08
    äre
    0.08
    Activations Density 0.010%

    No Known Activations