© 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 EvalsExportsinterp-engineNEWAPI 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. 54925
    Prev
    Next
    INDEX
    Explanations

    terms related to inaccuracies or falsehoods

    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
    lesi
    -0.07
    æķ¬
    -0.07
    anian
    -0.07
    .scalablytyped
    -0.06
    cakes
    -0.06
    oton
    -0.06
    ãĥŃãĥ¼
    -0.06
    اÙĨÙĪ
    -0.06
    ialized
    -0.06
    isson
    -0.06
    POSITIVE LOGITS
    fully
    0.09
    以为
    0.07
    do
    0.07
    fulness
    0.07
    /false
    0.07
     assumption
    0.07
     priorities
    0.07
     Ej
    0.06
    ripp
    0.06
     assumptions
    0.06
    Activations Density 0.016%

    No Known Activations