© 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. 89213
    Prev
    Next
    INDEX
    Explanations

    opinions and critiques related to social and political issues

    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
     actionTypes
    -0.07
    åºŃ
    -0.07
    Mahon
    -0.07
    .lex
    -0.06
    erg
    -0.06
    ourg
    -0.06
     cad
    -0.06
    ého
    -0.06
    ----------------------------------------------------------------------↵
    -0.06
    apur
    -0.06
    POSITIVE LOGITS
     than
    0.20
    -than
    0.17
    than
    0.15
     Than
    0.14
     THAN
    0.14
    Than
    0.13
    _than
    0.13
     än
    0.11
     než
    0.10
     niż
    0.09
    Activations Density 0.060%

    No Known Activations