© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 40510
    Prev
    Next
    INDEX
    Explanations

    phrases or topics related to contractual negotiations and their implications

    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
     inc
    -0.06
     Principal
    -0.06
     shitty
    -0.06
    eut
    -0.06
     obs
    -0.06
     brut
    -0.05
    kas
    -0.05
     TV
    -0.05
     èĩ
    -0.05
     ecosystem
    -0.05
    POSITIVE LOGITS
    azu
    0.08
    nave
    0.08
     Nets
    0.07
    ìĿ´ì§Ģ
    0.07
     addCriterion
    0.07
    ìĦłê±°
    0.07
     Web
    0.07
    alama
    0.07
     ByteArray
    0.07
    afari
    0.07
    Activations Density 0.001%

    No Known Activations