© 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. 55990
    Prev
    Next
    INDEX
    Explanations

    terms related to funeral services and memorial celebrations

    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
    ëįĶëĭĪ
    -0.06
    ces
    -0.06
    ansi
    -0.06
    ÑĨин
    -0.06
     Curl
    -0.06
    .getLocal
    -0.06
    obs
    -0.06
    θη
    -0.06
     dormant
    -0.06
     McDon
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.08
    ода
    0.07
    emma
    0.07
    =back
    0.07
    bish
    0.07
     eskort
    0.07
    setDisplay
    0.07
    igure
    0.07
    andest
    0.07
    oppable
    0.06
    Activations Density 0.002%

    No Known Activations