© 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. 17545
    Prev
    Next
    INDEX
    Explanations

    references to genetic testing procedures and their results

    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
    iska
    -0.07
    opa
    -0.07
    åŁ·
    -0.07
    olith
    -0.07
    isk
    -0.07
    alloca
    -0.06
    .IsChecked
    -0.06
    stras
    -0.06
    endale
    -0.06
    kinson
    -0.06
    POSITIVE LOGITS
     interpretation
    0.26
     Interpret
    0.24
     interpret
    0.23
    interpret
    0.22
     interpretations
    0.22
     interpreting
    0.20
     interpreted
    0.20
     interpre
    0.19
    interpre
    0.17
     interpreter
    0.16
    Activations Density 0.152%

    No Known Activations