© 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. 104375
    Prev
    Next
    INDEX
    Explanations

    references to cancer research organizations and their activities

    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
    hawk
    -0.07
    ierce
    -0.06
    indh
    -0.06
    anova
    -0.06
    undle
    -0.06
    odafone
    -0.06
    ologies
    -0.06
     union
    -0.06
    euillez
    -0.06
     Crown
    -0.06
    POSITIVE LOGITS
    .nih
    0.13
     Bethesda
    0.11
     NIH
    0.09
    @mail
    0.09
    RTC
    0.08
     NHL
    0.07
     Fog
    0.07
    avras
    0.07
    AMED
    0.07
    ÑĤÑİ
    0.07
    Activations Density 0.010%

    No Known Activations