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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 118494
    Prev
    Next
    INDEX
    Explanations

    financial transactions and payment details

    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
    <?↵
    -0.07
    ninger
    -0.07
    stadt
    -0.07
     didSet
    -0.06
    ngr
    -0.06
    ngth
    -0.06
    idine
    -0.06
     sometimes
    -0.06
     too
    -0.06
    jes
    -0.06
    POSITIVE LOGITS
    pec
    0.07
    ipeg
    0.07
    ibo
    0.06
    onde
    0.06
    Æ¡
    0.06
    tos
    0.06
    sdale
    0.06
    ActivityIndicatorView
    0.06
    á»įc
    0.06
     intermediate
    0.06
    Activations Density 0.016%

    No Known Activations