© 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. 15-LLAMASCOPE-RES-131K
    11. 157
    Prev
    Next
    INDEX
    Explanations

    mentions of programming libraries and frameworks

    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
    RACT
    -0.06
    atsby
    -0.06
     Fortress
    -0.06
    iem
    -0.06
    ync
    -0.06
    oty
    -0.06
    Ìģ
    -0.05
    ender
    -0.05
     åİ
    -0.05
     â
    -0.05
    POSITIVE LOGITS
    GMT
    0.08
    CEE
    0.07
    _strerror
    0.07
     èģĶ
    0.07
    .ul
    0.07
    .cx
    0.07
    تز
    0.07
    æ··åIJĪ
    0.07
    RLF
    0.07
    dbus
    0.06
    Activations Density 0.004%

    No Known Activations