© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 120745
    Prev
    Next
    INDEX
    Explanations

    the word "in" and its various usages throughout the text

    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
    orem
    -0.08
     iÅŁte
    -0.07
    roman
    -0.06
    ORM
    -0.06
    PLUS
    -0.06
    vest
    -0.06
    stad
    -0.06
    ories
    -0.06
    linear
    -0.06
    esco
    -0.06
    POSITIVE LOGITS
    AMED
    0.08
     certain
    0.08
    amed
    0.08
    plevel
    0.08
    ertain
    0.07
    ivent
    0.07
    Certain
    0.06
    еÑĪÑĮ
    0.06
     unlike
    0.06
    Ñij
    0.06
    Activations Density 0.051%

    No Known Activations