© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95611
    Prev
    Next
    INDEX
    Explanations

    references to countries and geographical locations

    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
     at
    -0.07
    âĢ¦↵
    -0.06
     set
    -0.06
     W
    -0.06
     pre
    -0.06
     base
    -0.06
     output
    -0.06
     s
    -0.06
    ural
    -0.06
     (
    -0.06
    POSITIVE LOGITS
    Å¡ak
    0.10
    ãİ
    0.09
    еÑĢеÑĩ
    0.08
    ifar
    0.08
    412
    0.08
    oÃłi
    0.08
     ActiveForm
    0.08
     >",
    0.08
    .edge
    0.08
    rq
    0.08
    Activations Density 0.015%

    No Known Activations