© 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. 119102
    Prev
    Next
    INDEX
    Explanations

    mentions of specific months and the level of activity associated with them

    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
    sky
    -0.06
    147
    -0.06
    elder
    -0.06
    148
    -0.06
    ]]>
    -0.06
    205
    -0.05
    140
    -0.05
     Vance
    -0.05
    149
    -0.05
     Official
    -0.05
    POSITIVE LOGITS
    ekil
    0.09
    otti
    0.07
    mini
    0.07
    ighth
    0.07
    oÄŁ
    0.07
    ettel
    0.07
    ÑĮ
    0.07
     Sokol
    0.06
    Äŀ
    0.06
    μεÏģο
    0.06
    Activations Density 0.005%

    No Known Activations