© 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. 5-LLAMASCOPE-RES-131K
    11. 125647
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be."

    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
     plain
    -0.07
    622
    -0.06
    ilet
    -0.06
    ouch
    -0.06
    zo
    -0.05
    olo
    -0.05
    zag
    -0.05
     Plain
    -0.05
    950
    -0.05
    ug
    -0.05
    POSITIVE LOGITS
    .onNext
    0.08
    coh
    0.08
    еÑĢб
    0.08
     Müz
    0.07
    ÑĤим
    0.07
    PÅĻed
    0.07
    okane
    0.07
    ivy
    0.07
    neath
    0.07
    uco
    0.07
    Activations Density 0.003%

    No Known Activations