© 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. 30010
    Prev
    Next
    INDEX
    Explanations

    URLs and hyperlinks

    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
    ::*
    -0.09
    endra
    -0.07
    .Slf
    -0.07
    oot
    -0.07
    /fixtures
    -0.07
    oda
    -0.07
    .metro
    -0.07
     eql
    -0.07
    leh
    -0.06
    olet
    -0.06
    POSITIVE LOGITS
    iani
    0.09
    Ĥ¬
    0.06
    vari
    0.06
    /
    0.06
     thanh
    0.06
    751
    0.06
    Ø·
    0.06
    и
    0.06
    hey
    0.06
    uchs
    0.06
    Activations Density 0.002%

    No Known Activations