© 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. 15-LLAMASCOPE-RES-131K
    6. 61338
    Prev
    Next
    INDEX
    Explanations

    phrases related to exploration or curiosity about surroundings

    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
    kok
    -0.07
    iom
    -0.07
    420
    -0.07
    roma
    -0.07
    enberg
    -0.07
    lém
    -0.07
    eyh
    -0.07
    vsp
    -0.06
    ipay
    -0.06
    igne
    -0.06
    POSITIVE LOGITS
    ŀ
    0.07
    ìĭ¬
    0.06
    706
    0.06
    ij
    0.06
    -ins
    0.06
     depths
    0.06
     fondo
    0.06
    depth
    0.06
    Coder
    0.06
     closely
    0.06
    Activations Density 0.011%

    No Known Activations