© 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. 54259
    Prev
    Next
    INDEX
    Explanations

    transitional phrases that indicate contrast 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
     also
    -0.06
     Also
    -0.06
    Also
    -0.06
     Already
    -0.06
     and
    -0.06
    also
    -0.05
     ar
    -0.05
     Notebook
    -0.05
    835
    -0.05
    ichel
    -0.05
    POSITIVE LOGITS
     never
    0.11
     ìĿ´ë²Ī
    0.11
     nunca
    0.11
     previous
    0.11
    never
    0.10
     bisher
    0.10
     previously
    0.10
     Never
    0.10
     nikdy
    0.09
     now
    0.09
    Activations Density 0.026%

    No Known Activations