© 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. 30752
    Prev
    Next
    INDEX
    Explanations

    phrases related to offers and services

    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
     Mur
    -0.07
    berger
    -0.06
     overhead
    -0.06
    .TabIndex
    -0.06
    ç·Ĵ
    -0.06
    ological
    -0.06
    پر
    -0.06
    alian
    -0.05
    ondon
    -0.05
    bers
    -0.05
    POSITIVE LOGITS
    acas
    0.07
    Peak
    0.07
    oltip
    0.07
     Peak
    0.07
    erialize
    0.07
    ái
    0.07
    _UNICODE
    0.07
    anter
    0.07
    badge
    0.07
    .MixedReality
    0.07
    Activations Density 0.009%

    No Known Activations