© 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. 124891
    Prev
    Next
    INDEX
    Explanations

    numeric representations of dates and statistics

    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
    olars
    -0.07
     whereas
    -0.07
    ocommerce
    -0.07
    .assertj
    -0.07
    ardon
    -0.07
    ibling
    -0.07
    arent
    -0.07
    jourd
    -0.07
    ungal
    -0.07
    elper
    -0.07
    POSITIVE LOGITS
    ĥĿ
    0.07
     Bü
    0.06
    ì°°
    0.06
    orno
    0.06
    à¸
    0.06
    oe
    0.06
    .Îł
    0.06
    ãĥªãĥ³ãĤ°
    0.06
     Matters
    0.06
    ëĥ
    0.06
    Activations Density 0.003%

    No Known Activations