© 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. 106275
    Prev
    Next
    INDEX
    Explanations

    assertions of knowledge and self-awareness in arguments

    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
    eed
    -0.06
     nag
    -0.06
    ach
    -0.06
     Kirby
    -0.06
    ãĤīãģĦ
    -0.06
    edi
    -0.06
    tries
    -0.06
    HashCode
    -0.05
     Mills
    -0.05
    try
    -0.05
    POSITIVE LOGITS
     neither
    0.08
    mund
    0.08
     pity
    0.07
    roti
    0.07
     never
    0.07
    gnore
    0.07
     NEVER
    0.07
     Strom
    0.07
     wäh
    0.07
    ç«¥
    0.07
    Activations Density 0.053%

    No Known Activations