© 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. 94581
    Prev
    Next
    INDEX
    Explanations

    instances of the past tense form of verbs

    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
    ebi
    -0.07
    erre
    -0.06
    acht
    -0.06
    agnost
    -0.06
     lite
    -0.06
    éĥij
    -0.06
     bib
    -0.06
     Andersen
    -0.06
    ç§ģãģ®
    -0.06
     anchor
    -0.06
    POSITIVE LOGITS
    ÙģÙĨ
    0.07
    bsite
    0.07
    bor
    0.07
    nova
    0.07
     Bands
    0.07
    á»±a
    0.06
     Satellite
    0.06
     Slayer
    0.06
    dw
    0.06
    bands
    0.06
    Activations Density 0.000%

    No Known Activations