© 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. 127481
    Prev
    Next
    INDEX
    Explanations

    financial performance indicators and reporting elements

    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
     Pais
    -0.06
    лл
    -0.06
    dek
    -0.06
    ilyn
    -0.06
    olo
    -0.06
    abad
    -0.06
    ire
    -0.06
    amma
    -0.06
    .community
    -0.05
    ILE
    -0.05
    POSITIVE LOGITS
    ibling
    0.08
    ainter
    0.07
    obil
    0.07
    зÑĭ
    0.07
    icont
    0.07
    rokes
    0.07
    ivent
    0.07
    chnitt
    0.06
    Issuer
    0.06
    ιο
    0.06
    Activations Density 0.001%

    No Known Activations