© 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. 17-LLAMASCOPE-RES-131K
    11. 126514
    Prev
    Next
    INDEX
    Explanations

    numerical statistics related to financial or market data

    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
    occo
    -0.06
    266
    -0.06
    ondo
    -0.06
    929
    -0.06
    ooth
    -0.06
    ells
    -0.05
    072
    -0.05
    ussia
    -0.05
    htar
    -0.05
    ãģªãģ©ãģ®
    -0.05
    POSITIVE LOGITS
     respectively
    0.23
     respective
    0.18
     ÑģооÑĤвеÑĤ
    0.14
    åĪĨåĪ«
    0.13
     resp
    0.12
     ê°ģê°ģ
    0.12
    respect
    0.12
    both
    0.11
     both
    0.10
    resp
    0.10
    Activations Density 0.047%

    No Known Activations