© 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. 15592
    Prev
    Next
    INDEX
    Explanations

    expressions related to offering assistance and solutions

    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
    Matchers
    -0.06
    ombs
    -0.06
    ÄįÃŃ
    -0.06
    _FM
    -0.06
    cplusplus
    -0.06
    éĩĬ
    -0.06
    allet
    -0.06
    amarin
    -0.06
    ylon
    -0.06
    -scalable
    -0.06
    POSITIVE LOGITS
     fits
    0.09
    fits
    0.07
     fit
    0.07
     help
    0.07
     helps
    0.07
     can
    0.07
     helping
    0.07
     Fits
    0.07
    urum
    0.06
    help
    0.06
    Activations Density 0.009%

    No Known Activations