© 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. 40511
    Prev
    Next
    INDEX
    Explanations

    references to specific cruise ships and their names

    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
    ceso
    -0.06
    à¸ģรรม
    -0.06
    rnd
    -0.06
    bron
    -0.06
     nature
    -0.06
     rem
    -0.06
    nds
    -0.06
    marvin
    -0.06
    ARAM
    -0.06
     mechan
    -0.06
    POSITIVE LOGITS
     herself
    0.08
    εÏĦ
    0.07
    íĺ¸
    0.07
    åı·
    0.07
    olley
    0.07
     adlı
    0.07
    -series
    0.06
    gens
    0.06
    è¿Ķ
    0.06
    ieri
    0.06
    Activations Density 0.029%

    No Known Activations