© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 62726
    Prev
    Next
    INDEX
    Explanations

    phrases that convey data, statistics, or results

    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
     необ
    -0.07
    ez
    -0.07
    yle
    -0.07
    èħķ
    -0.07
    ê´Ģ
    -0.07
    èĩ¨
    -0.07
    uant
    -0.07
    portun
    -0.07
    ά
    -0.07
    InSection
    -0.07
    POSITIVE LOGITS
     that
    0.12
     bahwa
    0.08
     rằng
    0.08
     a
    0.07
     it
    0.07
    0.07
    olars
    0.07
    een
    0.06
    olas
    0.06
     an
    0.06
    Activations Density 0.025%

    No Known Activations