© 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. 61029
    Prev
    Next
    INDEX
    Explanations

    phrases indicating organizational or institutional actions and developments

    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
    ij¸
    -0.07
    aldi
    -0.06
    ALA
    -0.06
    inen
    -0.06
    TRS
    -0.06
    ansi
    -0.06
    nám
    -0.06
    ãĥĸãĥª
    -0.06
    AMB
    -0.06
    нг
    -0.06
    POSITIVE LOGITS
    this
    0.08
    owi
    0.07
     NOW
    0.07
     this
    0.07
     tão
    0.07
     Cutting
    0.07
    è¿Ļä¹Ī
    0.07
    NOW
    0.06
    utr
    0.06
    å¦ĤæѤ
    0.06
    Activations Density 0.021%

    No Known Activations