© 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. 62057
    Prev
    Next
    INDEX
    Explanations

    terms related to legal rights and warranties

    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
    asar
    -0.08
     Ù¾ÚĺÙĪÙĩ
    -0.07
    ingleton
    -0.07
    inci
    -0.07
    ewe
    -0.07
    igham
    -0.07
    cki
    -0.07
    etur
    -0.07
    ت
    -0.07
    gran
    -0.07
    POSITIVE LOGITS
     Shapiro
    0.06
     Sheridan
    0.06
    oulder
    0.06
    spath
    0.06
     outr
    0.06
     Holl
    0.06
    olland
    0.06
     Gamb
    0.06
    ами
    0.05
    ä¾
    0.05
    Activations Density 0.000%

    No Known Activations