© 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. 129446
    Prev
    Next
    INDEX
    Explanations

    terms related to shortcuts and quick access 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
    argout
    -0.08
    houses
    -0.07
    .pkg
    -0.07
    oley
    -0.07
    overe
    -0.07
    ulet
    -0.07
    raci
    -0.07
    ÅĻeh
    -0.07
    سÙĪØ¨
    -0.06
     Keystone
    -0.06
    POSITIVE LOGITS
    aneous
    0.09
    ting
    0.08
    ory
    0.08
    stit
    0.07
    ism
    0.07
    arp
    0.07
    616
    0.06
    808
    0.06
    ennessee
    0.06
    ry
    0.06
    Activations Density 0.003%

    No Known Activations