© 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. 27703
    Prev
    Next
    INDEX
    Explanations

    measurements and descriptions related to stability and performance

    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
    Mods
    -0.07
    Graphic
    -0.07
    ynet
    -0.06
    íĦ
    -0.06
     cass
    -0.06
     Participation
    -0.06
     ActionListener
    -0.06
    öl
    -0.06
    zin
    -0.06
    adla
    -0.06
    POSITIVE LOGITS
     impress
    0.07
     overall
    0.07
     excellent
    0.07
     surprisingly
    0.07
     pill
    0.06
    osten
    0.06
     âĸ³
    0.06
    idel
    0.06
    iano
    0.06
    жÑĥ
    0.06
    Activations Density 0.008%

    No Known Activations