© 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. 73535
    Prev
    Next
    INDEX
    Explanations

    temporal phrases related to future actions or 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
     earlier
    -0.09
     Earlier
    -0.07
    .previous
    -0.07
     previous
    -0.07
     had
    -0.06
     Previous
    -0.06
    rett
    -0.06
     ÑĤогда
    -0.06
    awns
    -0.06
     last
    -0.06
    POSITIVE LOGITS
     upcoming
    0.13
     forthcoming
    0.10
     tomorrow
    0.10
     throughout
    0.10
     tonight
    0.10
    until
    0.10
     until
    0.09
    ä¸ĭåİ»
    0.09
     Until
    0.09
     Throughout
    0.09
    Activations Density 0.040%

    No Known Activations