© 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. 15-LLAMASCOPE-RES-131K
    11. 1504
    Prev
    Next
    INDEX
    Explanations

    phrases related to stock market recommendations and performance

    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
    -chan
    -0.07
    imeline
    -0.07
     fucks
    -0.07
    rotch
    -0.06
    chwitz
    -0.06
    ikipedia
    -0.06
    Trivia
    -0.06
    olen
    -0.06
    olio
    -0.06
    pees
    -0.06
    POSITIVE LOGITS
    atr
    0.06
    ÏĢÎŃ
    0.06
    itar
    0.06
    macros
    0.06
     picks
    0.06
    ist
    0.06
    STRU
    0.06
    ensively
    0.06
     ÑĢекомендÑĥ
    0.05
     sectors
    0.05
    Activations Density 0.010%

    No Known Activations