© 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. 15-LLAMASCOPE-RES-131K
    11. 26418
    Prev
    Next
    INDEX
    Explanations

    phrases related to experiences of lack or absence

    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
    JT
    -0.06
    /tiny
    -0.06
    kyt
    -0.06
    jon
    -0.06
    aft
    -0.06
     Ash
    -0.06
    ASH
    -0.06
     recip
    -0.06
    tık
    -0.06
    κÏħ
    -0.06
    POSITIVE LOGITS
     maz
    0.07
     ort
    0.07
     elim
    0.07
    immel
    0.06
    ancellable
    0.06
    ousel
    0.06
    acco
    0.06
     aile
    0.06
    avicon
    0.06
    prav
    0.06
    Activations Density 0.001%

    No Known Activations