© 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. 58974
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a financial transaction or one-time offers

    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
    /orders
    -0.07
    ữ
    -0.07
    sil
    -0.06
    137
    -0.06
    soever
    -0.06
    idel
    -0.06
     od
    -0.06
    quent
    -0.06
    764
    -0.06
     Od
    -0.06
    POSITIVE LOGITS
    /single
    0.11
    allon
    0.07
    -only
    0.07
    erview
    0.07
    tons
    0.07
    -use
    0.07
    /static
    0.07
    orarily
    0.07
    portun
    0.07
    TPL
    0.07
    Activations Density 0.006%

    No Known Activations