© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 4020
    Prev
    Next
    INDEX
    Explanations

    references to physical interactions and relationships

    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
     addCriterion
    -0.08
    еÑĤи
    -0.07
    oyo
    -0.07
    amburger
    -0.07
    ách
    -0.07
    èĥİ
    -0.06
    DRV
    -0.06
    èĪĮ
    -0.06
    å°ĸ
    -0.06
    urry
    -0.06
    POSITIVE LOGITS
     recip
    0.08
     mutual
    0.07
     recipro
    0.07
     exchanged
    0.07
    _exchange
    0.07
    ges
    0.06
     reciprocal
    0.06
     receivers
    0.06
     gesture
    0.06
     circulating
    0.06
    Activations Density 0.008%

    No Known Activations