© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 117341
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to the legitimacy and evaluation of service providers, particularly in the context of lotteries and shipping

    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
    .Raw
    -0.09
    itta
    -0.07
    apon
    -0.07
    akers
    -0.07
    iser
    -0.07
    宽
    -0.06
    _replace
    -0.06
    ot
    -0.06
    ãĥ¼ãĥŀ
    -0.06
    _cast
    -0.06
    POSITIVE LOGITS
     company
    0.09
     BBB
    0.08
    transparent
    0.08
    company
    0.07
     èī¯
    0.07
     transparent
    0.07
    uppy
    0.07
    quential
    0.07
    auga
    0.07
     vem
    0.07
    Activations Density 0.021%

    No Known Activations