© 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. 117739
    Prev
    Next
    INDEX
    Explanations

    topics related to regulatory affairs and consumer protection

    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
    rika
    -0.08
    екÑĤÑĥ
    -0.07
    Tho
    -0.07
    à¤Łà¤ķ
    -0.07
    _UNIT
    -0.07
    imei
    -0.07
    LastError
    -0.07
    ãĥ³ãĥĩãĤ£
    -0.06
    ieves
    -0.06
     unit
    -0.06
    POSITIVE LOGITS
    osh
    0.06
    antan
    0.06
    amat
    0.06
     Crist
    0.06
     News
    0.06
    åIJ¾
    0.06
     Dispatch
    0.06
     contract
    0.06
    uxt
    0.06
    175
    0.05
    Activations Density 0.005%

    No Known Activations