© 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. 41255
    Prev
    Next
    INDEX
    Explanations

    phrases related to verifying or ensuring correctness

    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
    CRE
    -0.07
    ã
    -0.07
    /by
    -0.06
    eco
    -0.06
     WithEvents
    -0.06
    HI
    -0.06
    Forward
    -0.06
    uxe
    -0.06
    umm
    -0.06
    ory
    -0.06
    POSITIVE LOGITS
     whether
    0.14
     Whether
    0.10
    æĺ¯åIJ¦
    0.10
    Whether
    0.09
    whether
    0.09
     WHETHER
    0.09
    SelfPermission
    0.08
    ä¸Ģä¸ĭ
    0.08
     progress
    0.08
     out
    0.07
    Activations Density 0.017%

    No Known Activations