© 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. 82105
    Prev
    Next
    INDEX
    Explanations

    references to differences and comparisons between groups or entities

    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
    chang
    -0.07
     hran
    -0.07
    .si
    -0.07
    Ïģθ
    -0.06
    uddle
    -0.06
    ile
    -0.06
    jure
    -0.06
     Benson
    -0.06
    chner
    -0.06
     Bart
    -0.06
    POSITIVE LOGITS
     experience
    0.08
    aland
    0.07
    between
    0.07
    ActionCreators
    0.07
    Brains
    0.07
    oler
    0.07
     between
    0.07
    experience
    0.07
    ongyang
    0.07
    iating
    0.07
    Activations Density 0.033%

    No Known Activations