© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 61530
    Prev
    Next
    INDEX
    Explanations

    terms related to finalists and competitive recognition

    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
    rey
    -0.07
    ilda
    -0.07
    keit
    -0.07
    ertz
    -0.06
    ÑĥлÑİ
    -0.06
    ilton
    -0.06
     primal
    -0.06
    wake
    -0.06
    /XML
    -0.06
    ahy
    -0.06
    POSITIVE LOGITS
    /win
    0.07
    /original
    0.07
    annon
    0.07
    Ñģен
    0.07
    epam
    0.07
    .ws
    0.07
    ESCO
    0.06
    atial
    0.06
    insic
    0.06
    =yes
    0.06
    Activations Density 0.004%

    No Known Activations