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

    Neuronpedia

    Jacobian LensNEW
    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. 130395
    Prev
    Next
    INDEX
    Explanations

    phrases related to encouragement and motivation in educational or leadership contexts

    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
    .pojo
    -0.07
    .printStackTrace
    -0.06
    subtype
    -0.06
    ateur
    -0.06
    ateurs
    -0.06
    å±
    -0.06
     getS
    -0.06
    isser
    -0.06
    eyse
    -0.06
    collapse
    -0.06
    POSITIVE LOGITS
     audience
    0.13
     Audience
    0.11
     attendees
    0.10
     everyone
    0.09
     participants
    0.09
     listeners
    0.09
     audiences
    0.09
    大家
    0.08
     Participants
    0.08
    everyone
    0.08
    Activations Density 0.034%

    No Known Activations