© 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. 108175
    Prev
    Next
    INDEX
    Explanations

    references to cancer-related genetic analysis and research

    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
    hoc
    -0.07
    adlo
    -0.07
    byss
    -0.07
    enton
    -0.07
    ãĤ¤ãĤº
    -0.07
     antlr
    -0.07
    anging
    -0.07
    /basic
    -0.07
    ีà¸Ķ
    -0.07
    claimer
    -0.07
    POSITIVE LOGITS
     cancer
    0.09
     Cancer
    0.09
     tum
    0.07
     tot
    0.06
     analysis
    0.06
     distinct
    0.06
     antic
    0.06
     churn
    0.06
     gam
    0.06
     Roose
    0.05
    Activations Density 0.009%

    No Known Activations