© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 83738
    Prev
    Next
    INDEX
    Explanations

    references to system errors and malfunctions

    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
    ία
    -0.06
    zin
    -0.06
    ainties
    -0.06
    Ø´Ùħ
    -0.06
    qui
    -0.06
    ias
    -0.06
    affe
    -0.06
    ny
    -0.06
     é¦
    -0.06
    å°½
    -0.06
    POSITIVE LOGITS
    indr
    0.08
    inspect
    0.07
     actual
    0.07
     ë³´ë©´
    0.07
     inspect
    0.07
     actually
    0.06
     appearing
    0.06
    rlen
    0.06
    ritt
    0.06
    ango
    0.06
    Activations Density 0.017%

    No Known Activations