© 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. 62139
    Prev
    Next
    INDEX
    Explanations

    instances of the word "it."

    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
    serter
    -0.07
     @{$
    -0.06
     _{}
    -0.06
    burgh
    -0.06
    915
    -0.06
    ìĹ¼
    -0.06
    .blur
    -0.06
    ahan
    -0.06
    ستÙĩ
    -0.06
    Ãło
    -0.06
    POSITIVE LOGITS
     happening
    0.08
     happen
    0.07
    innacle
    0.07
    ellido
    0.07
     happened
    0.07
     happens
    0.07
    lam
    0.07
    ÙĪÙĨØ©
    0.07
     konkrét
    0.06
    GetObject
    0.06
    Activations Density 0.038%

    No Known Activations