© 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. 87654
    Prev
    Next
    INDEX
    Explanations

    phrases related to requests and discoveries in research 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
    ExecutionContext
    -0.08
    ander
    -0.07
    važ
    -0.07
    GetInstance
    -0.06
     $($
    -0.06
    agma
    -0.06
    649
    -0.06
     huz
    -0.06
    inode
    -0.06
     province
    -0.06
    POSITIVE LOGITS
    åĢ«
    0.07
     lab
    0.07
     Nicholson
    0.07
     data
    0.07
     رÙĤ
    0.06
     grat
    0.06
    )prepare
    0.06
    ê´Ģ
    0.06
    .data
    0.06
     Grat
    0.06
    Activations Density 0.008%

    No Known Activations