© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 126193
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the."

    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
    utable
    -0.07
     обо
    -0.07
    enario
    -0.07
    üç
    -0.07
    ir
    -0.06
     entire
    -0.06
     Graz
    -0.06
     everywhere
    -0.06
    .Layer
    -0.06
    ont
    -0.06
    POSITIVE LOGITS
    ones
    0.08
    ht
    0.07
    hte
    0.07
     Banc
    0.07
     early
    0.07
     may
    0.06
    480
    0.06
     earliest
    0.06
    hta
    0.06
     other
    0.06
    Activations Density 0.034%

    No Known Activations