© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 80215
    Prev
    Next
    INDEX
    Explanations

    financial metrics and quantifiable data points related to investments and stock ratings

    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
    252
    -0.06
    esto
    -0.06
     se
    -0.06
    764
    -0.06
     unb
    -0.06
    ãng
    -0.06
     pil
    -0.06
    ↵↵
    -0.06
     Trot
    -0.06
    esModule
    -0.06
    POSITIVE LOGITS
     sole
    0.07
    eton
    0.07
    YO
    0.07
    EMALE
    0.07
    adiens
    0.06
    าà¸Ķ
    0.06
    ursor
    0.06
     interp
    0.06
    /stdc
    0.06
    è£ķ
    0.06
    Activations Density 0.002%

    No Known Activations