© 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 EvalsExportsinterp-engineNEWAPI 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. 95737
    Prev
    Next
    INDEX
    Explanations

    elements related to web development and programming concepts

    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
    ugas
    -0.07
    amura
    -0.07
    azor
    -0.06
    [
    -0.06
    ouis
    -0.06
    ierte
    -0.06
    uppe
    -0.06
    evin
    -0.06
    arent
    -0.06
    uestra
    -0.06
    POSITIVE LOGITS
     Gould
    0.08
    )":
    0.07
    ãĥīãĥ«
    0.07
    'order
    0.07
    .scalablytyped
    0.07
    HQ
    0.07
    FM
    0.07
     Andersen
    0.07
     doz
    0.06
    è²
    0.06
    Activations Density 0.050%

    No Known Activations