© 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. 130939
    Prev
    Next
    INDEX
    Explanations

    phrases associated with travel services and customer support

    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
    erea
    -0.07
    umont
    -0.07
    agues
    -0.07
    ague
    -0.07
    rodu
    -0.07
    ailing
    -0.06
    ingham
    -0.06
     alike
    -0.06
    alu
    -0.06
     however
    -0.06
    POSITIVE LOGITS
     ther
    0.07
     accordingly
    0.07
    ä¹Ī
    0.07
    .gf
    0.07
    zon
    0.07
    breadcrumbs
    0.06
    Iterable
    0.06
    .viewer
    0.06
     Dict
    0.06
    _nf
    0.06
    Activations Density 0.082%

    No Known Activations