© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29610
    Prev
    Next
    INDEX
    Explanations

    HTML and document structure 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
     éĥ
    -0.06
     eb
    -0.06
     пÑĢиÑĤ
    -0.06
    iste
    -0.06
    åİĭ
    -0.06
    umas
    -0.06
     Wan
    -0.06
     Association
    -0.06
     Unt
    -0.06
     Pep
    -0.06
    POSITIVE LOGITS
    /svg
    0.07
     rel
    0.06
    .TestTools
    0.06
    iloc
    0.06
     Spray
    0.06
    _triggered
    0.06
    aver
    0.06
    sez
    0.06
    >{@
    0.06
    CDATA
    0.06
    Activations Density 0.096%

    No Known Activations