© 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. 72443
    Prev
    Next
    INDEX
    Explanations

    terms related to film and visual storytelling

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

    Transitional elements and connective tokens that link textual components, particularly occurring at syntactic boundaries, in titles, or near formatting changes.

    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
    ê¼
    -0.07
    اذ
    -0.07
     оÑĤд
    -0.07
    ÙĪØ·
    -0.07
    _ENSURE
    -0.07
    ÐĴÑĤ
    -0.06
    _dma
    -0.06
    erez
    -0.06
    оÑģÑĥд
    -0.06
    .VisualBasic
    -0.06
    POSITIVE LOGITS
     The
    0.18
    The
    0.14
    /The
    0.13
     THE
    0.13
    /the
    0.13
    THE
    0.12
    	The
    0.11
    InThe
    0.11
     the
    0.11
    .The
    0.11
    Activations Density 0.300%

    No Known Activations