© 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. 108309
    Prev
    Next
    INDEX
    Explanations

    terms that indicate superiority or inferiority in comparison

    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
    away
    -0.08
    ych
    -0.07
    nel
    -0.07
    abouts
    -0.07
    ew
    -0.07
    eras
    -0.06
    ep
    -0.06
    åĦ¿
    -0.06
    osphere
    -0.06
     similarities
    -0.06
    POSITIVE LOGITS
    -quality
    0.10
    iors
    0.10
    ior
    0.09
    -most
    0.08
    ably
    0.08
    owl
    0.08
    iets
    0.07
     kiá»ĩn
    0.07
    haps
    0.07
    entially
    0.07
    Activations Density 0.006%

    No Known Activations