© 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. 57387
    Prev
    Next
    INDEX
    Explanations

    references to digital document identifiers and metadata

    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
     voks
    -0.07
    /Web
    -0.05
     letters
    -0.05
     Singleton
    -0.05
    ÙĪاÙĨ
    -0.05
    cope
    -0.05
     printable
    -0.05
     Leban
    -0.05
    aska
    -0.05
     rearr
    -0.05
    POSITIVE LOGITS
    è£ķ
    0.08
    -document
    0.08
    istrovstvÃŃ
    0.08
    abin
    0.07
    .scalablytyped
    0.07
    /bower
    0.07
    .Document
    0.07
    lect
    0.07
    ECT
    0.07
    окÑĥ
    0.07
    Activations Density 0.010%

    No Known Activations