© 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. 28954
    Prev
    Next
    INDEX
    Explanations

    repeated phrases or articles, particularly emphasizing 'the' and its variations

    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
     McDon
    -0.07
     slightest
    -0.07
    556
    -0.07
    меÑĩ
    -0.07
     McGregor
    -0.07
    Unavailable
    -0.07
    retch
    -0.07
    å¥
    -0.06
    ãĥ¼ãĥģ
    -0.06
    same
    -0.06
    POSITIVE LOGITS
     importance
    0.10
     why
    0.09
     role
    0.09
     ways
    0.08
     significance
    0.08
     recent
    0.08
     meaning
    0.07
     differences
    0.07
     prospects
    0.07
     how
    0.07
    Activations Density 0.029%

    No Known Activations