© 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. 57257
    Prev
    Next
    INDEX
    Explanations

    high-frequency use 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
    oque
    -0.07
    hq
    -0.07
    oucher
    -0.07
    ritch
    -0.07
    itan
    -0.07
    .transparent
    -0.07
    incerely
    -0.06
    Notifier
    -0.06
    iena
    -0.06
    ValueType
    -0.06
    POSITIVE LOGITS
    bes
    0.07
     Bram
    0.07
    ali
    0.06
    inke
    0.06
    Å¡lo
    0.06
    ani
    0.06
     Sun
    0.06
    ινÏĮ
    0.06
     Payne
    0.05
     Everett
    0.05
    Activations Density 0.036%

    No Known Activations