© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 59736
    Prev
    Next
    INDEX
    Explanations

    contexts involving emotional or physical states of individuals, particularly related to their needs or desires

    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
    isoft
    -0.07
    sequ
    -0.06
    xeb
    -0.06
    egot
    -0.06
    rement
    -0.06
     Sherman
    -0.06
    ardash
    -0.06
    éra
    -0.06
    reur
    -0.06
    abil
    -0.06
    POSITIVE LOGITS
     eben
    0.06
    iyah
    0.06
     stressful
    0.06
     Kits
    0.06
     bestimm
    0.06
    enger
    0.06
    essler
    0.06
     vigorously
    0.06
    iac
    0.06
     beneficiation
    0.06
    Activations Density 0.021%

    No Known Activations