© 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. 85899
    Prev
    Next
    INDEX
    Explanations

    terms related to climate and environmental temperature variability

    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
    inue
    -0.07
     jos
    -0.06
    mtx
    -0.06
     therapeutic
    -0.06
     muscular
    -0.06
    eter
    -0.05
     fé
    -0.05
     ser
    -0.05
     sû
    -0.05
    age
    -0.05
    POSITIVE LOGITS
     addCriterion
    0.09
     ensemble
    0.07
     ragaz
    0.07
    oppins
    0.07
    ookie
    0.07
    arella
    0.07
    SError
    0.07
    orks
    0.07
    ãĥĿãĤ¤ãĥ³ãĥĪ
    0.07
     NONINFRINGEMENT
    0.07
    Activations Density 0.173%

    No Known Activations