© 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. 80374
    Prev
    Next
    INDEX
    Explanations

    terms related to temporary or transient states and events

    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
    warts
    -0.07
    çİĩ
    -0.07
    icum
    -0.06
    iveness
    -0.06
    wij
    -0.06
    vÄĽ
    -0.06
    pic
    -0.06
    ë¦ī
    -0.06
    uff
    -0.06
    ç
    -0.06
    POSITIVE LOGITS
    orarily
    0.12
    /temp
    0.10
    oral
    0.09
    erture
    0.09
    orary
    0.08
    (Temp
    0.08
    reature
    0.08
    ory
    0.08
    uous
    0.07
    atures
    0.07
    Activations Density 0.028%

    No Known Activations