© 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. 95757
    Prev
    Next
    INDEX
    Explanations

    technical descriptions and details related to vulnerabilities and exploits

    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
    ignon
    -0.08
    okie
    -0.07
    òn
    -0.07
    æķ·
    -0.07
    hiba
    -0.06
     fontStyle
    -0.06
    SOR
    -0.06
    llvm
    -0.06
    .newaxis
    -0.06
    ",-
    -0.06
    POSITIVE LOGITS
    wig
    0.07
     reproduce
    0.07
    887
    0.07
     timings
    0.07
    .describe
    0.06
     describes
    0.06
     describe
    0.06
    891
    0.06
    ilder
    0.06
    °F
    0.06
    Activations Density 0.003%

    No Known Activations