© 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. 93958
    Prev
    Next
    INDEX
    Explanations

    numerical values and their ranges in a financial context

    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
    ninger
    -0.08
     approximate
    -0.06
    uyo
    -0.06
    asan
    -0.06
    unce
    -0.05
     payer
    -0.05
     kvin
    -0.05
    hoo
    -0.05
     fulfill
    -0.05
    623
    -0.05
    POSITIVE LOGITS
    ieu
    0.07
    reeze
    0.06
    åĿĤ
    0.06
     nearest
    0.06
    Äįné
    0.06
    lexport
    0.06
    itra
    0.06
    ieder
    0.06
    scribe
    0.06
    enant
    0.06
    Activations Density 0.014%

    No Known Activations