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

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 61498
    Prev
    Next
    INDEX
    Explanations

    references to documents, websites, or publications

    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
    mekte
    -0.08
     Thin
    -0.07
    ouri
    -0.07
    asco
    -0.06
    anki
    -0.06
    yna
    -0.06
    Thin
    -0.06
    anko
    -0.06
    akis
    -0.06
    aille
    -0.06
    POSITIVE LOGITS
    apyrus
    0.08
    avers
    0.08
    ISA
    0.07
     page
    0.07
    uber
    0.07
    odelist
    0.07
    icha
    0.07
    одÑĥ
    0.07
     !!}
    0.07
    gam
    0.06
    Activations Density 0.127%

    No Known Activations