© 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. 5-LLAMASCOPE-RES-131K
    11. 126893
    Prev
    Next
    INDEX
    Explanations

    terms associated with pressure, speed, and cooking techniques

    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
    ANGO
    -0.09
    eos
    -0.08
    ewire
    -0.08
    inish
    -0.08
    braco
    -0.07
    Jvm
    -0.07
    reachable
    -0.07
    ÃŃÅĻ
    -0.07
     пеÑĢен
    -0.07
    оÑĢаз
    -0.07
    POSITIVE LOGITS
    olas
    0.07
    ith
    0.06
     Lun
    0.06
     Acting
    0.06
    elsen
    0.06
     lod
    0.06
     lun
    0.06
     acting
    0.06
     Bentley
    0.06
    quo
    0.06
    Activations Density 0.001%

    No Known Activations