© 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. 105130
    Prev
    Next
    INDEX
    Explanations

    references to the name "Bob"

    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
    eren
    -0.08
    endon
    -0.07
    ene
    -0.07
    lý
    -0.07
    ldb
    -0.07
    'gc
    -0.07
    .scalablytyped
    -0.07
    ned
    -0.07
    Å¡ek
    -0.07
    uetype
    -0.06
    POSITIVE LOGITS
    bie
    0.10
    bi
    0.09
    bing
    0.08
    cat
    0.08
    би
    0.07
    alt
    0.07
    bers
    0.07
    ots
    0.07
    opup
    0.07
     mens
    0.07
    Activations Density 0.008%

    No Known Activations