© 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. 87022
    Prev
    Next
    INDEX
    Explanations

    phrases indicating statistical data or observations about community situations

    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
     mixed
    -0.06
    is
    -0.06
     margin
    -0.05
     wire
    -0.05
     proved
    -0.05
    M
    -0.05
     interesting
    -0.05
     intermitt
    -0.05
     customers
    -0.05
     occasionally
    -0.05
    POSITIVE LOGITS
     addCriterion
    0.10
     jadx
    0.10
    rschein
    0.09
    /Dk
    0.08
    DCALL
    0.08
    upal
    0.08
    qml
    0.08
    Subview
    0.08
    _multip
    0.08
    esiz
    0.08
    Activations Density 0.032%

    No Known Activations