© 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. 39260
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a lack or absence of something

    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
     being
    -0.06
    formation
    -0.06
    erty
    -0.06
    лож
    -0.06
    antar
    -0.06
    à¸Ńà¸Ħ
    -0.06
    annel
    -0.06
    仲
    -0.06
     nobody
    -0.06
    être
    -0.06
    POSITIVE LOGITS
    för
    0.07
    eniable
    0.07
    iggins
    0.07
     Borders
    0.06
    iated
    0.06
    $MESS
    0.06
    ëŀ
    0.06
    ock
    0.06
     regard
    0.06
    Bounding
    0.06
    Activations Density 0.013%

    No Known Activations