© 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. 71266
    Prev
    Next
    INDEX
    Explanations

    time indicators and specific timestamps

    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
    scribe
    -0.06
    ικο
    -0.06
    .onView
    -0.06
    vailability
    -0.06
    attachment
    -0.06
    phyl
    -0.06
     Ùħشار
    -0.06
     коÑĤоÑĢ
    -0.06
    alach
    -0.06
    stad
    -0.06
    POSITIVE LOGITS
    iyat
    0.07
     fun
    0.07
    ewater
    0.06
     Fun
    0.06
    folders
    0.06
    wat
    0.06
    odiac
    0.06
    Fun
    0.06
    reich
    0.06
    (IServiceCollection
    0.06
    Activations Density 0.004%

    No Known Activations