© 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. 77578
    Prev
    Next
    INDEX
    Explanations

    words that denote business-related concepts and transactions

    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
     оÑĩ
    -0.06
    arend
    -0.06
    htm
    -0.06
     bundled
    -0.06
    Advertisement
    -0.06
     åķ
    -0.06
    Advertisements
    -0.06
    aktu
    -0.05
     taped
    -0.05
    /cgi
    -0.05
    POSITIVE LOGITS
    needle
    0.07
     artists
    0.07
     gezocht
    0.07
     Needle
    0.07
    obj
    0.07
    avad
    0.07
     Sac
    0.07
    sek
    0.07
     möchten
    0.07
    ancia
    0.07
    Activations Density 0.000%

    No Known Activations