© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 27636
    Prev
    Next
    INDEX
    Explanations

    statements or phrases inviting participation or involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    A period/full stop at the end of a sentence that concludes information or an invitation, often appearing at the end of paragraphs where contact information, services offered, or procedural details are provided to readers.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     satellite
    -0.07
     Bond
    -0.06
     bonded
    -0.06
     Bonds
    -0.06
    iets
    -0.06
    ayer
    -0.06
    .jboss
    -0.06
    olley
    -0.06
    adesh
    -0.05
     Lyrics
    -0.05
    POSITIVE LOGITS
    emme
    0.09
    .scalablytyped
    0.08
    æķ
    0.07
    вана
    0.07
    -prepend
    0.07
    æ³ķ人
    0.07
    .Formatter
    0.07
    oÄŁ
    0.07
    .flat
    0.07
    èĹ
    0.07
    Activations Density 0.020%

    No Known Activations