© 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. 79572
    Prev
    Next
    INDEX
    Explanations

    mentions of durations of time, particularly relating to years and months

    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
    yan
    -0.07
    ryo
    -0.07
    yat
    -0.07
    ystems
    -0.06
    weed
    -0.06
    chop
    -0.06
    roti
    -0.06
    azel
    -0.06
    elm
    -0.06
    ESH
    -0.06
    POSITIVE LOGITS
    -long
    0.08
    nings
    0.07
     spent
    0.07
    ENDOR
    0.07
    ning
    0.07
    wis
    0.06
    lies
    0.06
    ACP
    0.06
    MMdd
    0.06
    леж
    0.06
    Activations Density 0.011%

    No Known Activations