© 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. 69452
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "was" and its various usages in contexts related to age and personal history

    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
    mbH
    -0.08
    phia
    -0.08
    ä¸ĢåĮº
    -0.08
     VÅ¡ech
    -0.07
     Ñĥм
    -0.07
     predecess
    -0.07
    isoft
    -0.07
     dispatch
    -0.07
    imei
    -0.07
    eton
    -0.06
    POSITIVE LOGITS
     young
    0.06
    art
    0.06
     ana
    0.06
     ber
    0.05
     sum
    0.05
    406
    0.05
     Jud
    0.05
     tre
    0.05
    657
    0.05
     old
    0.05
    Activations Density 0.008%

    No Known Activations