© 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. 92135
    Prev
    Next
    INDEX
    Explanations

    terms related to gene silencing and genetic processes

    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
    Qualifier
    -0.07
     rady
    -0.07
     Bund
    -0.07
    undle
    -0.06
    XMLLoader
    -0.06
    elder
    -0.06
     indir
    -0.06
    ynet
    -0.06
    itals
    -0.06
    _ARGUMENT
    -0.06
    POSITIVE LOGITS
     cond
    0.07
     barr
    0.07
    oti
    0.06
    olia
    0.06
    QueryString
    0.06
     formations
    0.06
     Ep
    0.06
     Toggle
    0.06
     mo
    0.06
     TArray
    0.06
    Activations Density 0.002%

    No Known Activations