© 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. 78040
    Prev
    Next
    INDEX
    Explanations

    sentences expressing certainty or inevitability

    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
    bourg
    -0.08
    alley
    -0.07
     proxy
    -0.06
    bote
    -0.06
    .debian
    -0.06
     Tas
    -0.06
    ĥ
    -0.06
     showc
    -0.06
     sad
    -0.06
     it
    -0.06
    POSITIVE LOGITS
    _HINT
    0.07
    doch
    0.07
    itis
    0.07
    jie
    0.06
    Ñĥда
    0.06
    å°½
    0.06
    SSION
    0.06
    Locator
    0.06
    ãģĸ
    0.06
    quential
    0.06
    Activations Density 0.031%

    No Known Activations