© 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. 78463
    Prev
    Next
    INDEX
    Explanations

    terms related to geographical and environmental features

    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
    ddit
    -0.08
    emoc
    -0.07
    etooth
    -0.07
    รร
    -0.07
    bildung
    -0.07
    .crm
    -0.07
    ạt
    -0.07
    лаб
    -0.07
    getc
    -0.07
    .scalablytyped
    -0.07
    POSITIVE LOGITS
     land
    0.07
    agram
    0.07
    andon
    0.06
     Donovan
    0.06
     Land
    0.06
     gre
    0.06
     Sext
    0.06
    /animate
    0.06
     polar
    0.06
     Bird
    0.05
    Activations Density 0.000%

    No Known Activations