© 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. 118535
    Prev
    Next
    INDEX
    Explanations

    phrases related to system integration and functionality

    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
     preced
    -0.07
    -Mart
    -0.07
     fare
    -0.07
    erval
    -0.06
     Valle
    -0.06
    guards
    -0.06
    аниÑĨ
    -0.06
    anner
    -0.06
    Var
    -0.06
    bonus
    -0.06
    POSITIVE LOGITS
    beck
    0.07
    alic
    0.07
    atır
    0.07
    affle
    0.06
    DataProvider
    0.06
     vo
    0.06
    asure
    0.06
     ëĮĢìłĦ
    0.06
    CANCEL
    0.06
    toMatch
    0.06
    Activations Density 0.042%

    No Known Activations