© 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. 69664
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their concentrations used for cleaning or sanitizing

    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
     draining
    -0.08
     wind
    -0.07
    wind
    -0.07
    Wind
    -0.07
    çłĤ
    -0.07
    ATRIX
    -0.06
     Drain
    -0.06
    oil
    -0.06
    asher
    -0.06
    drs
    -0.06
    POSITIVE LOGITS
    ùa
    0.07
    á»ijt
    0.07
    .staff
    0.07
    ipt
    0.07
     inline
    0.06
    .generated
    0.06
     HO
    0.06
     disproportion
    0.06
     Bron
    0.06
     settle
    0.06
    Activations Density 0.009%

    No Known Activations