© 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. 129439
    Prev
    Next
    INDEX
    Explanations

    directional instructions and numerical information related to travel

    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
    combe
    -0.07
    zik
    -0.07
    ultipart
    -0.06
    udeau
    -0.06
    otta
    -0.06
    ibus
    -0.06
     rapp
    -0.06
    Ĥ¤
    -0.06
    ONUS
    -0.06
    Beam
    -0.06
    POSITIVE LOGITS
     vo
    0.07
     foll
    0.07
     Pablo
    0.06
    emoc
    0.06
     Sheridan
    0.06
    omid
    0.06
    omon
    0.06
    ernet
    0.06
    _emit
    0.06
    'gc
    0.06
    Activations Density 0.004%

    No Known Activations