© 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. 120604
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "was."

    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
     nice
    -0.07
     Nice
    -0.06
    lbrace
    -0.06
     meiden
    -0.06
     partially
    -0.06
    nice
    -0.06
    çĤī
    -0.06
     Reeves
    -0.06
    nic
    -0.05
    985
    -0.05
    POSITIVE LOGITS
    osl
    0.08
    PÅĻi
    0.07
    ë¬
    0.07
    isor
    0.07
    ÏĦÎŃ
    0.07
    SSERT
    0.07
    ocket
    0.07
    usto
    0.07
    ENDOR
    0.07
    ocator
    0.07
    Activations Density 0.000%

    No Known Activations