© 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. 131049
    Prev
    Next
    INDEX
    Explanations

    numeric codes or identifiers related to scientific or technical documents

    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
    Į¨
    -0.07
    renal
    -0.07
    pository
    -0.06
    Å¡t
    -0.06
    enton
    -0.06
     ÑĥкÑĢаÑĹнÑģÑĮкоÑĹ
    -0.06
    editable
    -0.06
    oble
    -0.06
    ABA
    -0.06
    athi
    -0.06
    POSITIVE LOGITS
    mailto
    0.07
     Roz
    0.06
     departments
    0.06
     Katrina
    0.06
     Ark
    0.06
     department
    0.06
     Kr
    0.06
     affili
    0.05
    DOI
    0.05
     lif
    0.05
    Activations Density 0.000%

    No Known Activations