© 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. 408
    Prev
    Next
    INDEX
    Explanations

    expressions related to the length and quality of experiences or performances

    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
    PFN
    -0.09
     Lump
    -0.08
    readcr
    -0.08
    gons
    -0.08
    amiento
    -0.08
    anlık
    -0.08
    ATAR
    -0.08
    orget
    -0.07
    ukan
    -0.07
     openFileDialog
    -0.07
    POSITIVE LOGITS
     early
    0.07
     throughout
    0.06
    early
    0.06
     Initially
    0.06
    ox
    0.06
     my
    0.06
     myself
    0.06
     initially
    0.06
    oose
    0.06
     Pert
    0.06
    Activations Density 0.001%

    No Known Activations