© 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. 130968
    Prev
    Next
    INDEX
    Explanations

    function definitions and their constructors in code

    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
     Tone
    -0.07
    enes
    -0.07
     li
    -0.07
    опол
    -0.07
    ent
    -0.07
    acea
    -0.07
    ei
    -0.06
     sadd
    -0.06
     Albany
    -0.06
    ÎIJ
    -0.06
    POSITIVE LOGITS
    achine
    0.07
    auga
    0.07
    genden
    0.06
    ãĥĪãĥª
    0.06
    ırak
    0.06
    ulumi
    0.06
    fastcall
    0.06
    ugin
    0.06
    orris
    0.06
    371
    0.06
    Activations Density 0.001%

    No Known Activations