© 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. 22-LLAMASCOPE-RES-131K
    11. 3678
    Prev
    Next
    INDEX
    Explanations

    passive constructions and the presence of the verb "to be" in various tenses

    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
    vil
    -0.08
    ncoder
    -0.07
    ãĤ¤ãĤº
    -0.06
    #af
    -0.06
    -ÑĤо
    -0.06
    izzo
    -0.06
    estring
    -0.06
    supported
    -0.06
    ãģıãĤĮãģŁ
    -0.06
    ulf
    -0.06
    POSITIVE LOGITS
     considered
    0.24
     regarded
    0.18
     Consider
    0.17
     deemed
    0.17
     consider
    0.17
    consider
    0.16
     consid
    0.16
     considers
    0.16
     treated
    0.15
    Consider
    0.15
    Activations Density 0.075%

    No Known Activations