© 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. 70869
    Prev
    Next
    INDEX
    Explanations

    references to availability and access to online resources

    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
    idi
    -0.08
    ủy
    -0.06
     nano
    -0.06
    imonial
    -0.06
    ularity
    -0.06
    itti
    -0.06
    KANJI
    -0.06
    arto
    -0.06
    regor
    -0.06
     Pharmaceuticals
    -0.06
    POSITIVE LOGITS
     online
    0.07
    http
    0.06
    -selector
    0.06
     ç·
    0.06
    https
    0.06
    ì§ķ
    0.06
     Mile
    0.06
    brit
    0.06
    دÙĪ
    0.06
    окон
    0.06
    Activations Density 0.004%

    No Known Activations