© 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. 108173
    Prev
    Next
    INDEX
    Explanations

    references to travel arrangements and conditions related to planning

    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
    phan
    -0.07
    emez
    -0.07
    ickers
    -0.07
    icker
    -0.07
     ÑģÑĤанов
    -0.06
    antan
    -0.06
    ikal
    -0.06
    auté
    -0.06
    hardt
    -0.06
    çĶļèĩ³
    -0.06
    POSITIVE LOGITS
     somehow
    0.08
     implicitly
    0.08
    inea
    0.07
     assume
    0.07
     tac
    0.07
     assumed
    0.07
     already
    0.07
     ÙĪØ£ÙĨ
    0.07
     familiarity
    0.06
     Assume
    0.06
    Activations Density 0.051%

    No Known Activations