© 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. 15-LLAMASCOPE-RES-131K
    11. 86848
    Prev
    Next
    INDEX
    Explanations

    instances of data or statistics in a text

    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
    onga
    -0.06
     wol
    -0.06
    -devel
    -0.06
    ermann
    -0.06
     Newsp
    -0.06
    عاد
    -0.06
     compos
    -0.06
    inecraft
    -0.06
    itzer
    -0.06
     Replies
    -0.06
    POSITIVE LOGITS
     undone
    0.07
    pong
    0.06
    umb
    0.06
    Ø´ÙĨ
    0.06
    avy
    0.06
    actable
    0.06
    unnel
    0.06
    #ab
    0.06
    .documentElement
    0.06
    acer
    0.06
    Activations Density 0.004%

    No Known Activations