© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 130461
    Prev
    Next
    INDEX
    Explanations

    self-referential statements indicating knowledge or acknowledgment

    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
     misd
    -0.06
    sert
    -0.06
    è¿ŀ
    -0.06
    opo
    -0.06
    wis
    -0.06
    ãĥ¼ãĥ«ãĥī
    -0.06
    lix
    -0.06
    cus
    -0.06
     Bundy
    -0.05
    Ã¤ÃŁ
    -0.05
    POSITIVE LOGITS
     know
    0.14
     Know
    0.12
     knows
    0.11
    çŁ¥éģĵ
    0.09
    Know
    0.09
    know
    0.09
     KNOW
    0.09
     realize
    0.09
     çŁ¥
    0.08
     yes
    0.08
    Activations Density 0.047%

    No Known Activations