© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 116588
    Prev
    Next
    INDEX
    Explanations

    terms related to medical procedures and their implications

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Key terms describing variable attributes, quantities, or conditions, along with connecting words that establish relationships between concepts in explanatory or technical text.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219
    Triggered by @lu-christina
    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
    Negative Logits
    mis
    -0.07
    ominator
    -0.06
    allon
    -0.06
    _PAIR
    -0.06
    ahun
    -0.06
    ombok
    -0.06
    434
    -0.06
     twice
    -0.06
    lotte
    -0.06
     binder
    -0.06
    POSITIVE LOGITS
     depending
    0.13
     varies
    0.13
     vary
    0.13
    depending
    0.12
     exact
    0.11
     depends
    0.11
     Depending
    0.11
    Depending
    0.10
    depends
    0.10
    vary
    0.10
    Activations Density 0.085%

    No Known Activations