© 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. 126810
    Prev
    Next
    INDEX
    Explanations

    specific references to location and service-related details in a contract or informational text

    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
    sburg
    -0.09
    ussia
    -0.08
    寿
    -0.07
     YYS
    -0.07
    assin
    -0.07
    biên
    -0.07
    utherford
    -0.07
    .createClass
    -0.07
    Inlining
    -0.07
    .ca
    -0.07
    POSITIVE LOGITS
     Malta
    0.13
     Mediterranean
    0.10
     Mediterr
    0.08
     Sic
    0.07
    inja
    0.07
    orca
    0.07
     Leone
    0.07
     Tunis
    0.07
    Äł
    0.06
    Tiny
    0.06
    Activations Density 0.033%

    No Known Activations