© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 41186
    Prev
    Next
    INDEX
    Explanations

    references to trekking or hiking 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
    imary
    -0.07
    stantiate
    -0.07
     AVL
    -0.07
    nothrow
    -0.07
    etz
    -0.07
     cigaret
    -0.06
    AMP
    -0.06
    arend
    -0.06
    _TRNS
    -0.06
    Spy
    -0.06
    POSITIVE LOGITS
     route
    0.07
     circum
    0.06
     routes
    0.06
     Route
    0.06
     trek
    0.06
     provinces
    0.06
    acl
    0.06
     retr
    0.06
     discretionary
    0.05
    ismatic
    0.05
    Activations Density 0.012%

    No Known Activations