© 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. 117776
    Prev
    Next
    INDEX
    Explanations

    periods at the end of sentences

    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
     VOID
    -0.07
    prim
    -0.07
    alie
    -0.06
    ãģķãĤī
    -0.06
    KeyPress
    -0.06
     Fuse
    -0.06
    ãĥĹãĥª
    -0.06
    yro
    -0.06
    \brief
    -0.06
     #[
    -0.06
    POSITIVE LOGITS
    otal
    0.07
     straw
    0.07
    oux
    0.07
    ÄĽst
    0.06
    ebb
    0.06
    edm
    0.06
    engo
    0.06
    ech
    0.06
    ount
    0.06
     Erotik
    0.06
    Activations Density 0.004%

    No Known Activations