© 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. 83396
    Prev
    Next
    INDEX
    Explanations

    occurrences of the company name "Alibaba" and related terms

    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
    iras
    -0.07
    nett
    -0.07
    throp
    -0.06
    744
    -0.06
    ouse
    -0.06
    uong
    -0.06
    148
    -0.06
    229
    -0.06
    /ion
    -0.05
    lok
    -0.05
    POSITIVE LOGITS
    .fastjson
    0.08
    ê¸Ī
    0.08
    ITERAL
    0.08
    culate
    0.07
    entes
    0.07
    .gdx
    0.07
    apos
    0.07
     Îī
    0.07
    /Foundation
    0.07
    uter
    0.07
    Activations Density 0.001%

    No Known Activations