© 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. 30438
    Prev
    Next
    INDEX
    Explanations

    references to support and backing in political or industry-related contexts

    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
    æĿ
    -0.07
    iaux
    -0.07
    æ¨
    -0.06
    ahan
    -0.06
    aad
    -0.06
    plex
    -0.06
    IFn
    -0.06
     Kidd
    -0.06
    jf
    -0.06
    ItemAt
    -0.06
    POSITIVE LOGITS
     approval
    0.11
     backed
    0.10
     support
    0.10
     supported
    0.10
    approval
    0.10
     backing
    0.10
     Approval
    0.09
    supported
    0.09
     Supported
    0.09
     endorsement
    0.09
    Activations Density 0.074%

    No Known Activations