© 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. 15-LLAMASCOPE-RES-131K
    11. 62457
    Prev
    Next
    INDEX
    Explanations

    expressions of consumer expectations and demands for better services and choices

    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
    ainen
    -0.08
    .ManyToMany
    -0.07
    owe
    -0.07
    วà¸ĩ
    -0.07
    zk
    -0.07
    âłĢ
    -0.07
    Ñıв
    -0.07
    gle
    -0.07
    oogle
    -0.07
    .ALIGN
    -0.07
    POSITIVE LOGITS
     themselves
    0.07
     assurances
    0.06
     conveniently
    0.06
     incr
    0.06
    -caret
    0.06
     Flex
    0.06
     Jeb
    0.05
    енÑĭ
    0.05
     flexibility
    0.05
    nee
    0.05
    Activations Density 0.023%

    No Known Activations