© 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. 15-LLAMASCOPE-RES-131K
    11. 603
    Prev
    Next
    INDEX
    Explanations

    references to travel and adventure experiences

    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
    @testable
    -0.07
    ortex
    -0.07
    cherche
    -0.07
    _lite
    -0.07
    otec
    -0.07
    aterangepicker
    -0.07
    atars
    -0.07
    ATAR
    -0.07
    idis
    -0.07
    ainless
    -0.07
    POSITIVE LOGITS
     till
    0.07
     buck
    0.06
     Keystone
    0.06
    ãĥ¬ãĥĵ
    0.05
     getP
    0.05
     parte
    0.05
     city
    0.05
     Utt
    0.05
     Skill
    0.05
     peg
    0.05
    Activations Density 0.001%

    No Known Activations