© 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. 71874
    Prev
    Next
    INDEX
    Explanations

    occurrences of "forward-looking statements" in financial or corporate contexts

    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
    emy
    -0.07
    ogle
    -0.06
    iku
    -0.06
    stantiate
    -0.06
    kits
    -0.06
    ué
    -0.06
    ean
    -0.06
    ower
    -0.06
    verter
    -0.06
    u
    -0.06
    POSITIVE LOGITS
    رز
    0.07
     کاÙħ
    0.06
    (($
    0.06
    CTS
    0.06
    made
    0.06
     Zuk
    0.06
    CCCC
    0.06
     Nack
    0.06
     CFG
    0.06
    bases
    0.06
    Activations Density 0.001%

    No Known Activations