© 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. 79327
    Prev
    Next
    INDEX
    Explanations

    references to tutorials and guide-like content

    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
    IRC
    -0.07
    guard
    -0.07
    ansa
    -0.07
    nen
    -0.07
    fold
    -0.07
    /bus
    -0.06
    εÏĨ
    -0.06
    IBC
    -0.06
    edException
    -0.06
    еÑĢв
    -0.06
    POSITIVE LOGITS
    ship
    0.08
    matic
    0.08
    ists
    0.08
    ForObject
    0.07
    ships
    0.07
    ogue
    0.07
    ductory
    0.07
    ONTAL
    0.07
    ism
    0.07
    imestep
    0.07
    Activations Density 0.006%

    No Known Activations