© 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. 39438
    Prev
    Next
    INDEX
    Explanations

    references to alternative or additional entities and concepts

    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
    éri
    -0.07
    jos
    -0.06
    ùi
    -0.06
    ietet
    -0.06
     starting
    -0.06
    ãĥ¡ãĥ©
    -0.06
    ngen
    -0.06
    ungen
    -0.06
    eder
    -0.06
     treff
    -0.06
    POSITIVE LOGITS
    PerPixel
    0.07
     components
    0.06
    776
    0.06
     layers
    0.06
    ruba
    0.06
    -components
    0.06
    ennon
    0.06
    -Un
    0.06
    ByUrl
    0.06
     Elements
    0.06
    Activations Density 0.027%

    No Known Activations