© 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. 74410
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce conditional or situational 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
    onder
    -0.07
    ût
    -0.07
    estone
    -0.06
     Pitch
    -0.06
    sville
    -0.06
    edral
    -0.06
    WithOptions
    -0.06
    ibbon
    -0.06
    ska
    -0.06
     inh
    -0.06
    POSITIVE LOGITS
     Mana
    0.06
    Sizer
    0.06
    mana
    0.06
    lisi
    0.06
    issant
    0.06
     peer
    0.06
     små
    0.06
     Lis
    0.06
     Peer
    0.06
    Peer
    0.06
    Activations Density 0.003%

    No Known Activations