© 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. 39273
    Prev
    Next
    INDEX
    Explanations

    phrases indicating timeframes or conditions related to deadlines

    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
    ãĥĨãĥ«
    -0.07
    ủy
    -0.07
    zkum
    -0.07
    .mk
    -0.07
    vetica
    -0.07
    ór
    -0.07
     brun
    -0.07
    ares
    -0.07
    ouver
    -0.07
    alley
    -0.07
    POSITIVE LOGITS
     three
    0.08
    l
    0.07
     months
    0.06
     two
    0.06
     days
    0.06
    997
    0.06
     hours
    0.06
     calendar
    0.06
    oice
    0.06
    u
    0.06
    Activations Density 0.007%

    No Known Activations