© 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. 60409
    Prev
    Next
    INDEX
    Explanations

    elements related to television and movie listings or scheduling

    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
    erus
    -0.07
    MMdd
    -0.07
    >tag
    -0.07
     Leap
    -0.07
    arf
    -0.07
    adelphia
    -0.07
    Leap
    -0.07
    опÑĢоÑģ
    -0.07
    ovel
    -0.07
    ÏĦεÏģα
    -0.07
    POSITIVE LOGITS
     teaching
    0.06
    te
    0.06
     ‘
    0.06
     virtue
    0.06
    576
    0.05
     Teaching
    0.05
     subs
    0.05
    encion
    0.05
    eb
    0.05
     Sof
    0.05
    Activations Density 0.004%

    No Known Activations