© 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. 39987
    Prev
    Next
    INDEX
    Explanations

    future tense verbs indicating planned actions or intentions

    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
    459
    -0.07
    emi
    -0.07
    ù
    -0.07
    eyn
    -0.06
     Armour
    -0.06
     Tenn
    -0.06
    okino
    -0.06
     Exercise
    -0.06
    вад
    -0.06
    ickets
    -0.06
    POSITIVE LOGITS
     surely
    0.07
    fetch
    0.06
    Å¡tÃŃ
    0.06
    erge
    0.06
    Sure
    0.06
    oner
    0.06
    jin
    0.06
    eway
    0.06
    PEAT
    0.06
     Surely
    0.06
    Activations Density 0.042%

    No Known Activations