© 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. 22-LLAMASCOPE-RES-131K
    11. 3614
    Prev
    Next
    INDEX
    Explanations

    elements related to Forex trading and investment strategies

    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
    atak
    -0.07
    éħį
    -0.07
    /=
    -0.06
    ï¸ı
    -0.06
    еÑĢаÑħ
    -0.06
    @(
    -0.06
    ichert
    -0.06
    \Active
    -0.06
    icolon
    -0.06
     fich
    -0.06
    POSITIVE LOGITS
     tersebut
    0.07
    nya
    0.07
    zin
    0.07
     nÃło
    0.06
     yang
    0.06
     marvelous
    0.06
    izin
    0.06
    ogi
    0.06
    assis
    0.06
     Wend
    0.06
    Activations Density 0.007%

    No Known Activations