© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 60079
    Prev
    Next
    INDEX
    Explanations

    references to specific news organizations 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
    ading
    -0.07
    емон
    -0.06
    ogue
    -0.06
     Sanity
    -0.06
    ltr
    -0.06
    apy
    -0.06
    .serv
    -0.06
    uffy
    -0.06
    atra
    -0.06
    _radi
    -0.06
    POSITIVE LOGITS
     newspaper
    0.10
    ucker
    0.07
     magazine
    0.07
     Carrier
    0.07
     carrier
    0.07
     Magazine
    0.06
    社
    0.06
    /Framework
    0.06
    lesc
    0.06
     article
    0.06
    Activations Density 0.021%

    No Known Activations