© 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. 39833
    Prev
    Next
    INDEX
    Explanations

    references to government roles and functions

    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
    osu
    -0.07
    ì§
    -0.06
     stron
    -0.06
    reon
    -0.06
    ctor
    -0.06
    ÅĻez
    -0.06
    omu
    -0.06
    обÑĢаж
    -0.06
    urd
    -0.06
    rij
    -0.06
    POSITIVE LOGITS
     merely
    0.16
     simply
    0.13
    åıªæĺ¯
    0.11
     simplement
    0.11
     mere
    0.11
     only
    0.10
     juste
    0.10
     Simply
    0.10
     пÑĢоÑģÑĤо
    0.09
     instead
    0.09
    Activations Density 0.176%

    No Known Activations