© 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. 2053
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical or programming operations

    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
    bis
    -0.06
    vail
    -0.06
    iane
    -0.06
     canvas
    -0.06
     Dut
    -0.06
     Bender
    -0.06
     hull
    -0.06
    kel
    -0.06
    awl
    -0.05
    awai
    -0.05
    POSITIVE LOGITS
    åİħ
    0.07
     underst
    0.07
    idth
    0.06
    icontrol
    0.06
    bose
    0.06
     diam
    0.06
    anker
    0.06
     baÅŁta
    0.06
    ertype
    0.06
    715
    0.06
    Activations Density 0.000%

    No Known Activations