© 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. 57686
    Prev
    Next
    INDEX
    Explanations

    references to world news and global events

    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
    orum
    -0.07
    глÑı
    -0.07
    ulas
    -0.07
    ula
    -0.06
    ulumi
    -0.06
    анÑģ
    -0.06
    ustral
    -0.06
    ivor
    -0.06
     defaultMessage
    -0.06
    머ëĭĪ
    -0.06
    POSITIVE LOGITS
    wide
    0.09
     world
    0.08
    -wide
    0.07
     wide
    0.07
    /world
    0.07
     news
    0.07
    news
    0.07
    weit
    0.07
    okino
    0.06
    oje
    0.06
    Activations Density 0.009%

    No Known Activations