© 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. 16475
    Prev
    Next
    INDEX
    Explanations

    references to travel experiences and activities

    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
    _fh
    -0.08
    iker
    -0.08
    ráf
    -0.07
    irts
    -0.07
    ipop
    -0.07
    ATERIAL
    -0.07
    èį
    -0.07
    ilden
    -0.07
    adla
    -0.07
    ÑĢап
    -0.07
    POSITIVE LOGITS
     local
    0.08
     locals
    0.07
     street
    0.06
     religious
    0.06
     Paste
    0.06
    ç«ĭ
    0.06
     rice
    0.06
    local
    0.06
     Sum
    0.06
     hires
    0.05
    Activations Density 0.011%

    No Known Activations