© 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. 77342
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and regulatory implications

    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
    amble
    -0.07
    ensor
    -0.07
    SCRIPTOR
    -0.06
    .cgi
    -0.06
    alis
    -0.06
    oran
    -0.06
    athi
    -0.06
    isco
    -0.06
    &p
    -0.06
    Îŀ
    -0.06
    POSITIVE LOGITS
     might
    0.12
    might
    0.10
     potentially
    0.10
     Might
    0.09
     could
    0.09
     may
    0.09
     possibly
    0.09
    may
    0.09
     könnte
    0.09
     pourrait
    0.09
    Activations Density 0.062%

    No Known Activations