© 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. 17-LLAMASCOPE-RES-131K
    11. 83959
    Prev
    Next
    INDEX
    Explanations

    references to the city of Miami

    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
    .scalablytyped
    -0.10
    bos
    -0.07
    917
    -0.07
    .Unicode
    -0.07
    sk
    -0.07
    edly
    -0.07
    ancy
    -0.07
    chin
    -0.06
    shan
    -0.06
    dür
    -0.06
    POSITIVE LOGITS
    zym
    0.07
    ighter
    0.07
    agnost
    0.07
    apolis
    0.07
    fy
    0.07
    ServletRequest
    0.06
    atchet
    0.06
    aked
    0.06
    wald
    0.06
     fputs
    0.06
    Activations Density 0.006%

    No Known Activations