© 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. 94014
    Prev
    Next
    INDEX
    Explanations

    references to sponsors and committees in legislative texts

    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
    utan
    -0.07
    urname
    -0.07
    ighb
    -0.07
    оди
    -0.07
    ulas
    -0.06
    xEF
    -0.06
    ivating
    -0.06
    azon
    -0.06
    elper
    -0.06
     âĨĴ↵↵
    -0.06
    POSITIVE LOGITS
    iÄįka
    0.07
    Ñľ
    0.07
    Realm
    0.06
    idar
    0.06
    jian
    0.06
    iÄįky
    0.06
    .factor
    0.06
    gorm
    0.06
    Orm
    0.06
    blast
    0.06
    Activations Density 0.006%

    No Known Activations