© 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. 15-LLAMASCOPE-RES-131K
    11. 89948
    Prev
    Next
    INDEX
    Explanations

    phrases related to billing and invoicing

    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
    ÙĦÙĬÙĩ
    -0.07
    anes
    -0.06
    eland
    -0.06
    ingly
    -0.06
    dance
    -0.06
    acro
    -0.06
    gether
    -0.06
    994
    -0.06
     ur
    -0.06
     nullptr
    -0.06
    POSITIVE LOGITS
     fixed
    0.14
    fixed
    0.13
    Fixed
    0.12
    -fixed
    0.12
     Fixed
    0.12
    _fixed
    0.12
    åĽºå®ļ
    0.12
     FIXED
    0.11
    /static
    0.10
    .fixed
    0.10
    Activations Density 0.056%

    No Known Activations