© 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. 118410
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to court proceedings

    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
     trib
    -0.07
     hem
    -0.06
     gest
    -0.06
    tru
    -0.06
    emale
    -0.06
     lap
    -0.06
    nen
    -0.06
    hem
    -0.05
    OLLOW
    -0.05
     Kostenlos
    -0.05
    POSITIVE LOGITS
    ÄĻż
    0.08
    @qq
    0.07
    RPC
    0.07
    ıda
    0.07
    ì§ĢëıĦ
    0.07
    pcodes
    0.07
    pone
    0.07
    ucch
    0.07
    idan
    0.07
     cÃŃ
    0.07
    Activations Density 0.024%

    No Known Activations