© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 82315
    Prev
    Next
    INDEX
    Explanations

    inquiries related to hotel locations and nearby attractions

    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
    redient
    -0.07
     Fle
    -0.06
    licated
    -0.06
    å©Ĩ
    -0.06
    licate
    -0.06
    _Lean
    -0.06
    incer
    -0.06
    unft
    -0.06
     duty
    -0.06
    midt
    -0.06
    POSITIVE LOGITS
     distance
    0.09
     proximity
    0.09
    distance
    0.09
    .distance
    0.08
    Distance
    0.08
     nearest
    0.08
     distances
    0.08
     Distance
    0.08
    è·Ŀ离
    0.08
     clos
    0.08
    Activations Density 0.012%

    No Known Activations