© 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. 95083
    Prev
    Next
    INDEX
    Explanations

    references to enterprises or business ventures

    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
    ãĥĨãĥ«
    -0.10
    onn
    -0.08
    nya
    -0.08
    engeance
    -0.08
    utdown
    -0.08
    ski
    -0.08
    raz
    -0.08
    soever
    -0.07
    éĴŁ
    -0.07
    gne
    -0.07
    POSITIVE LOGITS
    -wide
    0.10
    wide
    0.08
    prising
    0.08
     Mahmoud
    0.07
    /start
    0.07
     wide
    0.06
    y
    0.06
    /in
    0.06
    of
    0.06
    able
    0.06
    Activations Density 0.006%

    No Known Activations