© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 31659
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to financial and investment topics

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    óÅĤ
    -0.07
    aille
    -0.07
    verter
    -0.07
    anager
    -0.07
    ifice
    -0.07
    /**č↵
    -0.06
    OwnProperty
    -0.06
    rais
    -0.06
    iphery
    -0.06
    stood
    -0.06
    POSITIVE LOGITS
    oret
    0.09
    etheless
    0.07
    ̣
    0.07
    okino
    0.07
    iou
    0.07
    oke
    0.07
    orem
    0.07
    zie
    0.07
    ories
    0.07
    oretical
    0.06
    Activations Density 0.144%

    No Known Activations