© 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. 86205
    Prev
    Next
    INDEX
    Explanations

    terms related to precipitation and its effects

    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
    acre
    -0.08
    mark
    -0.08
    liness
    -0.07
    ereal
    -0.07
    fully
    -0.07
    istry
    -0.07
     Spicer
    -0.06
    aking
    -0.06
    olie
    -0.06
    onomy
    -0.06
    POSITIVE LOGITS
    á»ijn
    0.08
    itous
    0.08
    ator
    0.08
    STANCE
    0.08
    виÑĤ
    0.08
    SOURCE
    0.08
    taÅŁ
    0.07
    itating
    0.07
    ante
    0.07
    ationToken
    0.07
    Activations Density 0.004%

    No Known Activations