© 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. 125154
    Prev
    Next
    INDEX
    Explanations

    mentions of policy initiatives and governmental commitments

    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
    anova
    -0.07
    nech
    -0.07
    ÑĢаÑħ
    -0.07
     è»
    -0.07
    ãĤ¥
    -0.07
     bò
    -0.06
    aldo
    -0.06
    chai
    -0.06
     affirmative
    -0.06
     Aydın
    -0.06
    POSITIVE LOGITS
     earlier
    0.08
     conven
    0.08
     å»
    0.08
    ennie
    0.07
     Additional
    0.07
     Hin
    0.06
     rst
    0.06
    716
    0.06
    la
    0.06
    235
    0.06
    Activations Density 0.032%

    No Known Activations