© 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. 9-LLAMASCOPE-RES-131K
    6. 95870
    Prev
    Next
    INDEX
    Explanations

    terms related to special or unique characteristics or features in various contexts

    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
    oss
    -0.07
    aments
    -0.07
    oria
    -0.06
    .va
    -0.06
    icon
    -0.06
    azÄĥ
    -0.06
    éĺħ读次æķ°
    -0.06
    ervas
    -0.06
    OOK
    -0.06
    ätz
    -0.06
    POSITIVE LOGITS
    amas
    0.07
    ovit
    0.06
    941
    0.06
    heat
    0.06
    ovsky
    0.06
    Ñģлов
    0.06
     Vz
    0.06
     Landing
    0.06
     jet
    0.06
     Sark
    0.06
    Activations Density 0.015%

    No Known Activations