© 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. 82097
    Prev
    Next
    INDEX
    Explanations

    terms related to promotions and product offers

    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
    ewe
    -0.08
    ildo
    -0.07
    azine
    -0.07
    mentions
    -0.07
    _gc
    -0.06
    æı®
    -0.06
    etimes
    -0.06
    лаж
    -0.06
    printStats
    -0.06
    ipel
    -0.06
    POSITIVE LOGITS
    ijkstra
    0.07
     ALERT
    0.06
    odka
    0.06
    elay
    0.06
    ward
    0.06
    AVOR
    0.06
    achs
    0.06
     Barn
    0.06
    âĨij
    0.06
    ichier
    0.06
    Activations Density 0.000%

    No Known Activations