© 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 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. 56123
    Prev
    Next
    INDEX
    Explanations

    references to timeframes and significant historical events

    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
    Ctl
    -0.07
    alf
    -0.06
    enco
    -0.06
    gon
    -0.06
    american
    -0.06
    uyu
    -0.06
    ainers
    -0.06
    chn
    -0.06
    855
    -0.06
    reh
    -0.06
    POSITIVE LOGITS
     Blitz
    0.08
    sert
    0.08
    ITERAL
    0.07
    uliar
    0.07
    chron
    0.07
    inel
    0.07
     refer
    0.07
    :event
    0.06
     chron
    0.06
    erty
    0.06
    Activations Density 0.000%

    No Known Activations