© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 71620
    Prev
    Next
    INDEX
    Explanations

    financial and investment-related information, particularly regarding shares and market values

    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
    lage
    -0.07
    odef
    -0.06
     upper
    -0.06
    338
    -0.06
    ÑĢÑİ
    -0.06
    ioni
    -0.06
    -Sah
    -0.05
    304
    -0.05
     Burton
    -0.05
     Davidson
    -0.05
    POSITIVE LOGITS
    _locked
    0.08
    CastException
    0.07
    GAN
    0.07
    ledi
    0.07
    _rights
    0.07
    окÑĢем
    0.07
    okin
    0.07
    ARA
    0.07
    أس
    0.06
    Å¡tÃŃ
    0.06
    Activations Density 0.008%

    No Known Activations