© 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. 117558
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" and their usages in various contexts

    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
    resse
    -0.06
    s
    -0.06
    atis
    -0.06
    erk
    -0.06
    odox
    -0.06
    embers
    -0.06
    Ùĩ
    -0.06
    rouch
    -0.06
    z
    -0.06
    asm
    -0.06
    POSITIVE LOGITS
    ey
    0.07
    eyin
    0.07
    adoo
    0.07
    åĢ«
    0.07
    inel
    0.07
    AMENT
    0.07
    ole
    0.07
    aurant
    0.07
    íķĻ
    0.06
    iteDatabase
    0.06
    Activations Density 0.003%

    No Known Activations