© 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. 9-LLAMASCOPE-RES-131K
    11. 96513
    Prev
    Next
    INDEX
    Explanations

    references to monetary values or pricing

    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
    ointed
    -0.07
    اتÙĩ
    -0.07
    nda
    -0.07
    appid
    -0.07
    ronym
    -0.07
    ubbo
    -0.07
    mund
    -0.07
    ircular
    -0.06
    relude
    -0.06
    OrUpdate
    -0.06
    POSITIVE LOGITS
    ing
    0.08
    anness
    0.08
    ness
    0.07
     doom
    0.07
    -American
    0.07
    UNCH
    0.07
    анка
    0.07
    phere
    0.07
    ries
    0.07
    (#)
    0.07
    Activations Density 0.010%

    No Known Activations