© 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. 128771
    Prev
    Next
    INDEX
    Explanations

    phrases related to disclaimers and warranties

    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
    cle
    -0.07
    _ABS
    -0.07
    ording
    -0.07
    azzi
    -0.06
    canf
    -0.06
    ÑĮогоднÑĸ
    -0.06
    stroy
    -0.06
    _perm
    -0.06
     Sek
    -0.06
    ATTRIBUTE
    -0.06
    POSITIVE LOGITS
    ayi
    0.07
     WARRANTIES
    0.07
     MERCHANTABILITY
    0.06
     unst
    0.06
     warranties
    0.06
    urance
    0.06
    ITICAL
    0.06
    avit
    0.06
     express
    0.06
     IMPLIED
    0.06
    Activations Density 0.001%

    No Known Activations