© 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. 70154
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols used in text formatting or trademark signs

    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
    mav
    -0.07
    ost
    -0.07
    gor
    -0.06
    oken
    -0.06
     Wass
    -0.06
    etary
    -0.06
    ek
    -0.06
    ous
    -0.06
    oller
    -0.06
    itan
    -0.06
    POSITIVE LOGITS
    lobe
    0.07
     Garner
    0.07
    loff
    0.07
    Spaces
    0.07
    å®Ļ
    0.07
    Į
    0.07
    uell
    0.07
    วà¸ģ
    0.07
    reste
    0.07
    IRST
    0.06
    Activations Density 0.001%

    No Known Activations