© 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. 39501
    Prev
    Next
    INDEX
    Explanations

    contrasting phrases or statements in texts

    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
    laz
    -0.07
    ħ
    -0.07
    opup
    -0.07
    allo
    -0.07
    ãĤ«ãĥĨãĤ´ãĥª
    -0.07
    CRET
    -0.07
    bas
    -0.07
     mặc
    -0.07
    ãĥ¬ãĥ³
    -0.06
    .getProperties
    -0.06
    POSITIVE LOGITS
    antal
    0.07
    ầy
    0.07
     still
    0.07
     why
    0.07
     Decompiled
    0.07
     plenty
    0.06
    enk
    0.06
     maybe
    0.06
    raid
    0.06
    umann
    0.06
    Activations Density 0.023%

    No Known Activations