© 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. 125786
    Prev
    Next
    INDEX
    Explanations

    references to ticket sales and event information

    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
    BackStack
    -0.06
    нен
    -0.06
     minib
    -0.06
    akt
    -0.06
     sequ
    -0.05
    563
    -0.05
    ä¹
    -0.05
    icker
    -0.05
     åĢ
    -0.05
     ÑĤе
    -0.05
    POSITIVE LOGITS
    çĶ£
    0.08
    aise
    0.07
     Offline
    0.07
    offline
    0.07
    CRET
    0.07
    igy
    0.07
    uros
    0.07
    Offline
    0.06
    ãĥ¬ãĥĥãĥĪ
    0.06
    è¬
    0.06
    Activations Density 0.008%

    No Known Activations