© 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. 77258
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions and illegitimate charges

    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
    veau
    -0.07
    ica
    -0.06
    ê·¼
    -0.06
    hora
    -0.06
    izo
    -0.06
    éĢĶ
    -0.06
    mk
    -0.06
    openh
    -0.06
    iqué
    -0.06
    opping
    -0.06
    POSITIVE LOGITS
     services
    0.09
    ISTR
    0.07
    /licenses
    0.07
    services
    0.07
    -services
    0.07
     Blanch
    0.06
    altura
    0.06
    rish
    0.06
    Ñıл
    0.06
     pred
    0.06
    Activations Density 0.021%

    No Known Activations