© 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. 74856
    Prev
    Next
    INDEX
    Explanations

    economic proposals and their anticipated effects

    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
    679
    -0.07
    991
    -0.07
    quine
    -0.07
    (æľ¨
    -0.06
    ideo
    -0.06
     Tarif
    -0.06
     خر
    -0.06
    .space
    -0.06
    ÏĥÏĥ
    -0.06
    PLE
    -0.06
    POSITIVE LOGITS
    aroo
    0.06
    agos
    0.06
    arro
    0.06
     estimate
    0.06
     overall
    0.06
     Virt
    0.06
     $
    0.06
    isel
    0.06
    imator
    0.06
     estimates
    0.06
    Activations Density 0.019%

    No Known Activations