© 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. 17-LLAMASCOPE-RES-131K
    11. 119991
    Prev
    Next
    INDEX
    Explanations

    references to various facets or components of a topic

    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
    sz
    -0.08
    dy
    -0.08
    rup
    -0.08
    esco
    -0.07
    ãģ¾ãģŁ
    -0.07
    DonaldTrump
    -0.07
    avic
    -0.07
    oria
    -0.06
    MARK
    -0.06
    space
    -0.06
    POSITIVE LOGITS
    ual
    0.09
    ually
    0.08
    urnal
    0.07
    pects
    0.07
    ively
    0.07
    eking
    0.07
    inite
    0.07
    ureka
    0.07
    imes
    0.07
    dns
    0.07
    Activations Density 0.008%

    No Known Activations