© 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. 3430
    Prev
    Next
    INDEX
    Explanations

    references to historical events and artifacts

    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
    alles
    -0.07
    à¹īà¸ĩ
    -0.06
    rum
    -0.06
    ãģıãĤĵ
    -0.06
    ardi
    -0.06
    ìĤ¬ëĬĶ
    -0.06
    گاÙĩÛĮ
    -0.06
     íij¸
    -0.06
    orp
    -0.06
     Morm
    -0.06
    POSITIVE LOGITS
     older
    0.16
     old
    0.15
    older
    0.15
     ancient
    0.14
     Older
    0.13
    196
    0.13
     oldest
    0.12
    197
    0.12
     early
    0.12
    193
    0.12
    Activations Density 0.071%

    No Known Activations