© 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. 78622
    Prev
    Next
    INDEX
    Explanations

    code structures or programming syntax

    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
    umann
    -0.07
    orum
    -0.07
    aurus
    -0.06
    rej
    -0.06
    ream
    -0.06
    legacy
    -0.06
    landing
    -0.06
    imits
    -0.06
     pun
    -0.06
    /rec
    -0.06
    POSITIVE LOGITS
     return
    0.17
    return
    0.14
    	return
    0.14
    {return
    0.12
     Return
    0.10
    -return
    0.10
    )return
    0.10
    Return
    0.10
     returned
    0.10
    :return
    0.09
    Activations Density 0.022%

    No Known Activations