© 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. 61028
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing frequency or occurrence

    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
    erken
    -0.07
    itm
    -0.07
     hrom
    -0.07
    PU
    -0.06
    ognito
    -0.06
    çĶ¨çļĦ
    -0.06
    ستÙĩ
    -0.06
    HELL
    -0.06
    assin
    -0.06
     pros
    -0.06
    POSITIVE LOGITS
     iteration
    0.07
    ë§Īëĭ¤
    0.07
    ding
    0.07
    icot
    0.07
    itecture
    0.06
    δα
    0.06
    cord
    0.06
    ãĤ·ãĥ¼
    0.06
    ime
    0.06
    kip
    0.06
    Activations Density 0.015%

    No Known Activations