© 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. 5-LLAMASCOPE-RES-131K
    11. 126433
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "end" in various contexts

    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
    ammad
    -0.07
    [".
    -0.07
    fern
    -0.07
    oni
    -0.07
    eting
    -0.07
    ete
    -0.07
    oma
    -0.07
     اÙĦÙĨÙĪ
    -0.07
     Hag
    -0.07
    Îŀ
    -0.07
    POSITIVE LOGITS
     Livingston
    0.06
     either
    0.05
    ainless
    0.05
    ĸī
    0.05
     GPL
    0.05
    缼
    0.05
     both
    0.05
    ouden
    0.05
     Ex
    0.05
    ød
    0.05
    Activations Density 0.005%

    No Known Activations