© 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. 29683
    Prev
    Next
    INDEX
    Explanations

    events related to entertainment and performances

    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
     hostel
    -0.07
    ÑĢиз
    -0.07
    åħĪçĶŁ
    -0.06
     puta
    -0.06
    .PL
    -0.06
    наÑĢ
    -0.06
    åĦĢ
    -0.06
    иÑĩа
    -0.06
     punch
    -0.06
    arters
    -0.06
    POSITIVE LOGITS
    ensch
    0.06
     Arena
    0.06
     Consumer
    0.06
     Hockey
    0.06
     arena
    0.06
     MetroFramework
    0.06
     Whe
    0.06
    sequ
    0.06
    stown
    0.06
    çĴ
    0.06
    Activations Density 0.003%

    No Known Activations