© 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. 16759
    Prev
    Next
    INDEX
    Explanations

    phrases associated with offers and estimates related to services and consultations

    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
    aza
    -0.08
    اض
    -0.07
    als
    -0.07
    urgeon
    -0.06
    ald
    -0.06
    mand
    -0.06
     Blasio
    -0.06
    ADDE
    -0.06
     Ald
    -0.06
    oyal
    -0.06
    POSITIVE LOGITS
    stup
    0.07
     contact
    0.07
     or
    0.07
    太éĥİ
    0.07
     schedule
    0.07
    ano
    0.06
     either
    0.06
     Contact
    0.06
    either
    0.06
     call
    0.06
    Activations Density 0.015%

    No Known Activations