© 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. 117809
    Prev
    Next
    INDEX
    Explanations

    instances of contrast or exception within a 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
    vice
    -0.07
    /lic
    -0.07
    racat
    -0.07
    Å¡ti
    -0.07
    imus
    -0.06
    emoth
    -0.06
     kéo
    -0.06
    Ø´ÙĪ
    -0.06
     èŤ
    -0.06
     vice
    -0.06
    POSITIVE LOGITS
     none
    0.10
     ones
    0.08
     one
    0.08
     few
    0.08
    ones
    0.08
     only
    0.07
     None
    0.07
     Among
    0.07
    none
    0.07
     certain
    0.07
    Activations Density 0.024%

    No Known Activations