© 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. 87586
    Prev
    Next
    INDEX
    Explanations

    the term "other" in various contexts

    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
    edly
    -0.06
    adoo
    -0.06
    amba
    -0.06
     çĤ
    -0.06
    ãĥ£
    -0.06
    enton
    -0.06
     further
    -0.06
     descon
    -0.06
    uku
    -0.05
    ellen
    -0.05
    POSITIVE LOGITS
     two
    0.10
     three
    0.09
     beiden
    0.09
    two
    0.08
    iator
    0.08
    411
    0.07
    anca
    0.07
    @nate
    0.07
     две
    0.07
    three
    0.07
    Activations Density 0.016%

    No Known Activations