© 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. 28283
    Prev
    Next
    INDEX
    Explanations

    references to chemical compounds or scientific terms related to material science

    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
    amam
    -0.08
    ertest
    -0.07
     Hindered
    -0.07
    lod
    -0.07
    ÑĤаж
    -0.07
    antt
    -0.07
    xsd
    -0.07
    amoto
    -0.07
    iteral
    -0.07
    acd
    -0.07
    POSITIVE LOGITS
     Han
    0.06
     Native
    0.06
    ëŁī
    0.06
    spiel
    0.05
     Fritz
    0.05
    ged
    0.05
     sf
    0.05
    çĪ·
    0.05
    976
    0.05
     Er
    0.05
    Activations Density 0.022%

    No Known Activations