© 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. 59676
    Prev
    Next
    INDEX
    Explanations

    references to online sources or websites

    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
    oday
    -0.06
    \.
    -0.06
    rug
    -0.06
    áng
    -0.06
    etrofit
    -0.06
     Rowe
    -0.06
    ла
    -0.06
    rror
    -0.06
    è§Ĥçľĭ
    -0.06
    åįļçī©
    -0.06
    POSITIVE LOGITS
    oldem
    0.07
    isure
    0.07
    ensa
    0.06
    riere
    0.06
    erland
    0.06
     vit
    0.06
    èijĹ
    0.06
     cris
    0.06
    hazi
    0.06
    ê
    0.06
    Activations Density 0.065%

    No Known Activations