© 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. 79705
    Prev
    Next
    INDEX
    Explanations

    affirmations and summaries related to recipes or instructions

    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
    jac
    -0.06
    reso
    -0.06
    Solo
    -0.06
    اÙģت
    -0.06
     Solo
    -0.06
    335
    -0.06
    íĥ
    -0.06
    wich
    -0.06
    berger
    -0.06
    antine
    -0.06
    POSITIVE LOGITS
     completes
    0.07
    unbind
    0.07
    wal
    0.07
     complete
    0.06
    ourcem
    0.06
     exhaust
    0.06
     ends
    0.06
    NAMESPACE
    0.06
    rough
    0.06
     xong
    0.06
    Activations Density 0.011%

    No Known Activations