© 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. 92640
    Prev
    Next
    INDEX
    Explanations

    discussions about deficiencies or gaps in information or knowledge

    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
    issement
    -0.07
    ÄĽÅ¾
    -0.06
    Ø´ÙĪر
    -0.06
    contres
    -0.06
    noinspection
    -0.06
    ضÙĦ
    -0.06
     Utf
    -0.06
     mne
    -0.06
    ého
    -0.06
     kabil
    -0.06
    POSITIVE LOGITS
     gaps
    0.22
     gap
    0.20
    gap
    0.18
     holes
    0.17
     Gap
    0.17
    Gap
    0.17
    -gap
    0.16
     hole
    0.15
     missing
    0.15
    _gap
    0.15
    Activations Density 0.092%

    No Known Activations