© 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. 15-LLAMASCOPE-RES-131K
    11. 89954
    Prev
    Next
    INDEX
    Explanations

    references to the United States and its government structure

    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
     knull
    -0.06
    WARE
    -0.06
    ût
    -0.06
    éŀ
    -0.06
    apore
    -0.06
    opsis
    -0.06
    Æ°á»Ľ
    -0.06
    ienes
    -0.06
    annes
    -0.06
     Newtown
    -0.06
    POSITIVE LOGITS
    izr
    0.07
     Bowman
    0.06
    å¯
    0.06
    kaz
    0.06
    £i
    0.06
    Pod
    0.06
    _CHANGED
    0.06
     l
    0.05
    areth
    0.05
    è¾°
    0.05
    Activations Density 0.007%

    No Known Activations