© 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. 5-LLAMASCOPE-RES-131K
    11. 125650
    Prev
    Next
    INDEX
    Explanations

    instances of the word "were" in various contexts

    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
    جاÙħ
    -0.07
    erton
    -0.07
    sel
    -0.07
    омеÑĢ
    -0.07
    dge
    -0.06
    onium
    -0.06
    vailability
    -0.06
    tr
    -0.06
    istra
    -0.06
    ard
    -0.06
    POSITIVE LOGITS
     chem
    0.06
    UNG
    0.06
    æij
    0.06
    à¥įà¤Ĺत
    0.06
    stile
    0.06
     trium
    0.06
    ibles
    0.06
    esz
    0.06
    lád
    0.06
    ASET
    0.06
    Activations Density 0.010%

    No Known Activations