© 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. 15-LLAMASCOPE-RES-131K
    11. 90266
    Prev
    Next
    INDEX
    Explanations

    specific geographical locations or organizations

    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
    ondo
    -0.08
    wing
    -0.07
    ilst
    -0.07
     Bbw
    -0.06
    еÐ
    -0.06
    alu
    -0.06
    âĢİ
    -0.06
     rast
    -0.06
     Roses
    -0.06
     dist
    -0.06
    POSITIVE LOGITS
    /Card
    0.09
    ians
    0.08
    ian
    0.07
    opup
    0.07
    ese
    0.07
    Å¡tÃŃ
    0.07
    eters
    0.07
    -Compatible
    0.07
    ibold
    0.07
    _reserved
    0.07
    Activations Density 0.009%

    No Known Activations