© 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 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. 58595
    Prev
    Next
    INDEX
    Explanations

    names of companies and corporations

    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
    à¸Ńà¸Ļà¸Ķ
    -0.07
    FIELDS
    -0.07
    rollo
    -0.07
    bsub
    -0.07
    OND
    -0.07
     babes
    -0.07
    çª
    -0.07
    onse
    -0.07
     createState
    -0.06
    verbosity
    -0.06
    POSITIVE LOGITS
     discounted
    0.06
     owner
    0.06
     Corp
    0.06
    owner
    0.06
    360
    0.06
    æ¯Ľ
    0.06
    ุม
    0.06
     sna
    0.06
     last
    0.06
    atts
    0.06
    Activations Density 0.024%

    No Known Activations