© 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. 58402
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "once" and its context in past experiences or statements

    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
     today
    -0.08
     newest
    -0.08
     latest
    -0.07
    usta
    -0.07
    ocoder
    -0.07
     tonight
    -0.06
    .edu
    -0.06
    alat
    -0.06
    ague
    -0.06
    llib
    -0.06
    POSITIVE LOGITS
     Kear
    0.07
    -times
    0.07
    elen
    0.07
    attempt
    0.06
     remarked
    0.06
     briefly
    0.06
     remark
    0.06
    æľī人
    0.06
     EntityState
    0.06
    ãģĤãĤĭ
    0.06
    Activations Density 0.011%

    No Known Activations