© 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. 127333
    Prev
    Next
    INDEX
    Explanations

    percentages and related statistics about material products

    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
    enums
    -0.07
    gr
    -0.07
    .scalablytyped
    -0.06
    CUS
    -0.06
     shepherd
    -0.06
     plano
    -0.06
    ãĤ¾
    -0.06
    cus
    -0.06
    ãĥ³ãĤ¿
    -0.06
    лев
    -0.06
    POSITIVE LOGITS
    IJ
    0.07
    åĴ²
    0.06
    igue
    0.06
    atego
    0.06
    968
    0.06
    uce
    0.06
    /he
    0.06
    arend
    0.06
    attend
    0.06
    é¦Ļ
    0.06
    Activations Density 0.002%

    No Known Activations