© 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. 22-LLAMASCOPE-RES-131K
    11. 3693
    Prev
    Next
    INDEX
    Explanations

    opportunities for engagement and interaction

    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
    .scalablytyped
    -0.07
    èo
    -0.07
    éĽĦ
    -0.07
    InitStruct
    -0.07
    anggal
    -0.07
    çħ§
    -0.07
     gratuiti
    -0.07
    ZX
    -0.07
     Invite
    -0.07
     недел
    -0.06
    POSITIVE LOGITS
     ask
    0.14
     Ask
    0.13
    Ask
    0.13
    ask
    0.12
     asking
    0.11
    ASK
    0.11
    _ask
    0.11
     asks
    0.10
     learn
    0.10
     meet
    0.10
    Activations Density 0.018%

    No Known Activations