© 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. 88679
    Prev
    Next
    INDEX
    Explanations

    references to items or properties that are available for sale

    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
    ingly
    -0.06
    ily
    -0.06
    ly
    -0.06
    ship
    -0.06
    @qq
    -0.06
     Buyers
    -0.06
    /r
    -0.06
     sequ
    -0.06
    us
    -0.06
    /s
    -0.06
    POSITIVE LOGITS
    ĵåIJį
    0.09
    .libs
    0.08
    epam
    0.08
    /by
    0.07
    istrovstvÃŃ
    0.07
    Ïħγ
    0.07
    abled
    0.07
    onet
    0.07
    تÙĦ
    0.07
    ynn
    0.07
    Activations Density 0.005%

    No Known Activations