© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 71199
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the start of experiences or relationships

    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
     ÐŁÑĢа
    -0.07
    retain
    -0.07
     early
    -0.07
    borg
    -0.06
    ouce
    -0.06
    лагод
    -0.06
     earlier
    -0.06
    recent
    -0.06
    esi
    -0.06
    agna
    -0.06
    POSITIVE LOGITS
    nings
    0.10
     something
    0.08
    /end
    0.07
    ä¸Ģç§į
    0.07
    º
    0.07
     began
    0.07
     Begins
    0.07
     begins
    0.07
     begun
    0.07
    ıt
    0.06
    Activations Density 0.013%

    No Known Activations