© 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. 15-LLAMASCOPE-RES-131K
    11. 90135
    Prev
    Next
    INDEX
    Explanations

    references to classified information and related processes

    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
    ĸī
    -0.06
     drain
    -0.06
     Exhaust
    -0.06
    /respond
    -0.06
     СÑĢед
    -0.06
     Newman
    -0.06
     Ziel
    -0.06
    allee
    -0.06
    ÑģÑĸм
    -0.06
    obo
    -0.06
    POSITIVE LOGITS
    nds
    0.07
     Marine
    0.07
     sensitive
    0.07
    classified
    0.07
    leared
    0.07
     Pent
    0.06
    wright
    0.06
    ê¸ī
    0.06
    Sensitive
    0.06
     Foreign
    0.06
    Activations Density 0.005%

    No Known Activations