© 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 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. 88340
    Prev
    Next
    INDEX
    Explanations

    financial performance indicators related to stock market movements

    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
    esian
    -0.07
    	templateUrl
    -0.06
     Ramp
    -0.06
    526
    -0.06
    andi
    -0.06
    etary
    -0.05
    sz
    -0.05
     Gross
    -0.05
    _FWD
    -0.05
     Rede
    -0.05
    POSITIVE LOGITS
     immediate
    0.08
    ãĥ¨
    0.07
    लब
    0.07
    omit
    0.07
    ardu
    0.07
    .datab
    0.07
     immediately
    0.07
    BackColor
    0.06
    OnInit
    0.06
    _HOOK
    0.06
    Activations Density 0.008%

    No Known Activations