© 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. 15875
    Prev
    Next
    INDEX
    Explanations

    phrases related to mathematical models and their properties

    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
    ON
    -0.07
    ween
    -0.07
    meld
    -0.06
    æŁ´
    -0.06
     Oliv
    -0.06
    //}}
    -0.06
    ersen
    -0.06
    ippi
    -0.06
     hopefully
    -0.06
    NEWS
    -0.06
    POSITIVE LOGITS
     indeed
    0.10
     actually
    0.10
    actually
    0.08
     Indeed
    0.08
     surprisingly
    0.08
    竣
    0.07
     Actually
    0.07
    Actually
    0.07
    Indeed
    0.07
     can
    0.07
    Activations Density 0.093%

    No Known Activations