© 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. 125573
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and their geopolitical contexts

    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
    iami
    -0.07
     Ghana
    -0.07
    icago
    -0.07
    IEW
    -0.07
     Kansas
    -0.07
    unga
    -0.06
    äre
    -0.06
     Egyptian
    -0.06
     Rajasthan
    -0.06
    rysler
    -0.06
    POSITIVE LOGITS
     Kashmir
    0.10
     Baltimore
    0.08
     JK
    0.08
     Balt
    0.08
    dna
    0.07
    JK
    0.07
    BOSE
    0.07
     Belfast
    0.07
    oin
    0.07
    chk
    0.07
    Activations Density 0.008%

    No Known Activations