© 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. 61588
    Prev
    Next
    INDEX
    Explanations

    elements of nature and landscapes

    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
    ɵ
    -0.07
    amo
    -0.06
    Äįel
    -0.06
    Äįil
    -0.06
    SpaceItem
    -0.06
    HostException
    -0.06
    οÏħÏĤ
    -0.06
    .qual
    -0.06
    UsageId
    -0.06
    .ordinal
    -0.06
    POSITIVE LOGITS
    BILE
    0.07
    ivic
    0.07
    igs
    0.07
    arty
    0.06
    ilha
    0.06
    uish
    0.06
    obar
    0.06
    terminal
    0.06
    neck
    0.06
    Ïģθ
    0.06
    Activations Density 0.000%

    No Known Activations