© 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. 72710
    Prev
    Next
    INDEX
    Explanations

    mention of awards or prizes related to specific criteria

    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
    utos
    -0.06
    ÅĪ
    -0.06
    Æ°á»Ŀng
    -0.06
     consequence
    -0.06
    ensors
    -0.06
     affairs
    -0.06
    à¹ĩà¸ĩ
    -0.06
    286
    -0.06
    248
    -0.06
    eni
    -0.06
    POSITIVE LOGITS
     access
    0.07
    XObject
    0.07
     priorit
    0.07
     Plantae
    0.07
    yll
    0.07
     priority
    0.07
    agua
    0.07
    éĢģæĸĻçĦ¡æĸĻ
    0.07
     oportun
    0.07
     chance
    0.06
    Activations Density 0.016%

    No Known Activations