© 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. 15-LLAMASCOPE-RES-131K
    11. 86631
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'by'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The word "by" introducing the agent or means through which an action is performed or completed, typically following passive voice constructions or verbs indicating an action being carried out.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    abay
    -0.09
    KeySpec
    -0.08
    enou
    -0.08
    IBUTE
    -0.08
    ibrary
    -0.08
    amiliar
    -0.08
    EditingStyle
    -0.08
    ControlItem
    -0.08
    gnore
    -0.08
    ORIZONTAL
    -0.08
    POSITIVE LOGITS
     means
    0.12
    -products
    0.11
     virtue
    0.11
    products
    0.10
     the
    0.09
    /to
    0.08
    -pass
    0.08
     chance
    0.08
     a
    0.08
    gone
    0.08
    Activations Density 0.341%

    No Known Activations