© 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. 15-LLAMASCOPE-RES-131K
    11. 88186
    Prev
    Next
    INDEX
    Explanations

    phrases and terms associated with malfunctioning or non-functioning devices

    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
    RuntimeObject
    -0.07
    isque
    -0.07
    imo
    -0.06
    zcze
    -0.06
    pac
    -0.06
    æı
    -0.06
    iggins
    -0.06
    imli
    -0.06
    Ø°
    -0.06
    OKIE
    -0.06
    POSITIVE LOGITS
     function
    0.07
    eral
    0.06
     Function
    0.06
    ê·¹
    0.06
     stranded
    0.06
    pond
    0.06
     burned
    0.06
    pector
    0.06
     raising
    0.06
     func
    0.06
    Activations Density 0.013%

    No Known Activations