© 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. 1729
    Prev
    Next
    INDEX
    Explanations

    instances of the word "but" and expressions that introduce contrasts or shifts in narrative

    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
    reator
    -0.07
    çĶ
    -0.07
    iov
    -0.06
    ÑĢÑıд
    -0.06
    ogle
    -0.06
    éis
    -0.06
    emean
    -0.06
    enis
    -0.06
    ifen
    -0.06
     Kingdom
    -0.06
    POSITIVE LOGITS
     eventually
    0.11
     soon
    0.11
     ultimately
    0.10
    Eventually
    0.09
     nakonec
    0.08
     Eventually
    0.08
     eventual
    0.08
     upon
    0.08
     opak
    0.08
     Ultimately
    0.07
    Activations Density 0.021%

    No Known Activations