© 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. 95495
    Prev
    Next
    INDEX
    Explanations

    phrases indicating time duration or specific time intervals

    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
    oyo
    -0.08
    stead
    -0.07
    essler
    -0.07
    sey
    -0.07
    overe
    -0.07
    ëŀij
    -0.07
    üh
    -0.07
    lero
    -0.06
    Lens
    -0.06
     erm
    -0.06
    POSITIVE LOGITS
    éĴŁ
    0.12
    -long
    0.10
    éIJĺ
    0.10
    aneously
    0.09
    aries
    0.09
    aneous
    0.08
     ago
    0.08
    ary
    0.08
    roc
    0.07
    long
    0.07
    Activations Density 0.015%

    No Known Activations