© 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. 15-LLAMASCOPE-RES-131K
    11. 87366
    Prev
    Next
    INDEX
    Explanations

    instances of the word "record" and its variations

    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
     gens
    -0.06
    ç²¾
    -0.06
    erator
    -0.06
    دÙĪ
    -0.06
    chten
    -0.06
    orado
    -0.06
    êu
    -0.06
    647
    -0.06
    263
    -0.06
    reau
    -0.05
    POSITIVE LOGITS
    number
    0.09
    -breaking
    0.09
     amount
    0.08
     number
    0.08
    amount
    0.07
    -record
    0.07
    TEGER
    0.07
     Minerals
    0.07
    breaking
    0.07
     record
    0.07
    Activations Density 0.009%

    No Known Activations