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

    Neuronpedia

    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. 9-LLAMASCOPE-RES-131K
    11. 95843
    Prev
    Next
    INDEX
    Explanations

    references to bone marrow and its role in blood production

    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
    tion
    -0.07
    ÑĩаÑģÑĤ
    -0.07
    chter
    -0.07
    [:]
    -0.07
    vars
    -0.06
    _framework
    -0.06
    relude
    -0.06
    --------------------------------------------------------------------------↵
    -0.06
    tam
    -0.06
    nio
    -0.06
    POSITIVE LOGITS
    oog
    0.06
    itemid
    0.06
    lÃŃÄį
    0.06
    گاÙĩ
    0.06
    åĪ¸
    0.06
     TAR
    0.06
    inden
    0.06
    ncy
    0.06
     ApplicationUser
    0.06
     gross
    0.06
    Activations Density 0.004%

    No Known Activations