© 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. 84351
    Prev
    Next
    INDEX
    Explanations

    phrases indicating prior knowledge or awareness about a situation or event

    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
    øy
    -0.07
    urtle
    -0.07
     now
    -0.07
    arov
    -0.07
    830
    -0.07
    alsy
    -0.07
    vik
    -0.07
    elay
    -0.06
    SqlParameter
    -0.06
    iska
    -0.06
    POSITIVE LOGITS
     sooner
    0.08
     ÑģÑİ
    0.07
    hest
    0.07
    &page
    0.06
    ]={↵
    0.06
    znam
    0.06
    çak
    0.06
    ymb
    0.06
    printer
    0.06
    ceph
    0.06
    Activations Density 0.022%

    No Known Activations