© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 89637
    Prev
    Next
    INDEX
    Explanations

    references to specific calendar dates

    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
     GRE
    -0.06
    ç¯
    -0.06
     hyp
    -0.06
     <$
    -0.06
     CASE
    -0.06
     Zag
    -0.06
    alom
    -0.06
    alf
    -0.05
     proh
    -0.05
     excl
    -0.05
    POSITIVE LOGITS
    ithe
    0.08
    istor
    0.07
    fo
    0.07
    ãĥ¼ãĤ¹ãĥĪ
    0.07
    radan
    0.06
    egend
    0.06
    ested
    0.06
     mesel
    0.06
    otel
    0.06
     uncomment
    0.06
    Activations Density 0.000%

    No Known Activations