© 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. 27055
    Prev
    Next
    INDEX
    Explanations

    terms related to medical and technical services

    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
    iales
    -0.06
    's
    -0.06
    ottes
    -0.06
    iffe
    -0.06
    ture
    -0.06
    aben
    -0.06
    ancell
    -0.06
    Çİ
    -0.06
    uries
    -0.06
    -chan
    -0.06
    POSITIVE LOGITS
    tiv
    0.07
     опÑĭÑĤ
    0.07
    ONY
    0.07
    essler
    0.06
    еж
    0.06
    lenÃŃ
    0.06
    εια
    0.06
     ÙĨÙħ
    0.06
    vů
    0.06
    νοÏį
    0.06
    Activations Density 0.047%

    No Known Activations