© 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. 130018
    Prev
    Next
    INDEX
    Explanations

    punctuations and sentence endings

    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
    Additionally
    -0.08
     Gee
    -0.07
    Regardless
    -0.07
    ilst
    -0.07
     Additionally
    -0.07
    VP
    -0.07
     Whilst
    -0.06
    emma
    -0.06
    umber
    -0.06
     Everywhere
    -0.06
    POSITIVE LOGITS
    -plus
    0.08
    TEGER
    0.07
     plus
    0.07
     yes
    0.06
    ìĦŃ
    0.06
     OK
    0.06
     pronto
    0.06
    jÃŃm
    0.06
    jac
    0.06
     resc
    0.06
    Activations Density 0.193%

    No Known Activations