© 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 EvalsExportsAPI 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. 16492
    Prev
    Next
    INDEX
    Explanations

    references to the artist Solomon and related terms

    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
    isman
    -0.07
    NOP
    -0.07
    ford
    -0.07
    ibbon
    -0.07
    lined
    -0.06
    aos
    -0.06
    .localized
    -0.06
    wald
    -0.06
    jes
    -0.06
    hardt
    -0.06
    POSITIVE LOGITS
    uble
    0.08
    berger
    0.07
    omon
    0.07
    itaire
    0.07
    sterol
    0.07
     Sol
    0.07
     stol
    0.06
    stitial
    0.06
    aptop
    0.06
    zano
    0.06
    Activations Density 0.027%

    No Known Activations