© 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. 9-LLAMASCOPE-RES-131K
    11. 98289
    Prev
    Next
    INDEX
    Explanations

    references to the United States and its government actions

    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
    oire
    -0.08
    esel
    -0.07
     immobil
    -0.07
    atha
    -0.07
    loth
    -0.07
    utsch
    -0.07
    assi
    -0.07
    ëį¸
    -0.06
    éľ²åĩº
    -0.06
    lds
    -0.06
    POSITIVE LOGITS
     TRI
    0.06
    ervas
    0.06
    rium
    0.06
    éĹ
    0.06
    Nat
    0.06
    657
    0.06
    feito
    0.06
    ectar
    0.06
    asion
    0.05
     infer
    0.05
    Activations Density 0.014%

    No Known Activations