© 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. 89630
    Prev
    Next
    INDEX
    Explanations

    instances of location and direction within the text

    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
    ffa
    -0.07
    837
    -0.06
    ukt
    -0.06
    636
    -0.06
    تا
    -0.05
     diff
    -0.05
    ANEL
    -0.05
     meg
    -0.05
     Latter
    -0.05
     figure
    -0.05
    POSITIVE LOGITS
     here
    0.12
     aquÃŃ
    0.10
    here
    0.09
    è¿ĻéĩĮ
    0.09
     здеÑģÑĮ
    0.09
     اÛĮÙĨجا
    0.08
     aqui
    0.08
     ici
    0.08
    _here
    0.08
    aset
    0.07
    Activations Density 0.045%

    No Known Activations