© 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. 17-LLAMASCOPE-RES-131K
    11. 94288
    Prev
    Next
    INDEX
    Explanations

    discussions about values, structures, and principles in various 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
    iyim
    -0.07
    ắc
    -0.07
     reliably
    -0.07
     rady
    -0.07
    yyy
    -0.06
     intermitt
    -0.06
    ä¼ı
    -0.06
    iffe
    -0.06
     besides
    -0.06
    IfNeeded
    -0.06
    POSITIVE LOGITS
     instead
    0.18
    instead
    0.17
     rather
    0.15
     Instead
    0.14
    Instead
    0.14
    rather
    0.13
     вмеÑģÑĤ
    0.12
     Rather
    0.12
    Rather
    0.11
     statt
    0.10
    Activations Density 0.049%

    No Known Activations