© 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. 9-LLAMASCOPE-RES-131K
    11. 95575
    Prev
    Next
    INDEX
    Explanations

    references to weather conditions and environmental measurements

    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
    ayet
    -0.08
    eless
    -0.07
    velte
    -0.07
    æ·¡
    -0.07
    \common
    -0.07
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    -0.07
    à¸ļà¸Ħ
    -0.07
    eah
    -0.07
    enberg
    -0.07
    .clf
    -0.07
    POSITIVE LOGITS
     poj
    0.07
     Picks
    0.07
     Patton
    0.06
     loc
    0.06
    IMS
    0.06
    fal
    0.06
    ima
    0.06
    903
    0.06
    adan
    0.05
    olis
    0.05
    Activations Density 0.052%

    No Known Activations