© 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. 17-LLAMASCOPE-RES-131K
    11. 120041
    Prev
    Next
    INDEX
    Explanations

    capital letters that likely represent various organizations or entities

    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
     McL
    -0.06
    ORY
    -0.06
    arius
    -0.06
     Them
    -0.06
     Campos
    -0.06
     Mitt
    -0.06
    Ìģt
    -0.05
     Teh
    -0.05
    .dst
    -0.05
    313
    -0.05
    POSITIVE LOGITS
    rende
    0.08
    ikat
    0.07
    IFEST
    0.07
    ãĥ³ãĥĩ
    0.07
    iyi
    0.07
     {{--<
    0.07
    ẹp
    0.06
    itere
    0.06
    ิà¸į
    0.06
     mot
    0.06
    Activations Density 0.047%

    No Known Activations