© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 96054
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate inclusion or enumeration

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Common transitional phrases and connectors that introduce examples or additional information, particularly "such as," "including," and "are" when they precede lists or elaborations.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219
    Triggered 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
    Negative Logits
     hete
    -0.08
     proje
    -0.07
     consc
    -0.07
     descargar
    -0.07
     strav
    -0.07
     cade
    -0.07
    ëŁ
    -0.07
     roli
    -0.07
    ied
    -0.07
    null
    -0.07
    POSITIVE LOGITS
     downright
    0.06
    aget
    0.06
     Morr
    0.06
    ãĥ³ãĤ°ãĥ«
    0.06
    $MESS
    0.06
    CreateDate
    0.06
    Ìī
    0.06
    abilidade
    0.05
    pector
    0.05
     http
    0.05
    Activations Density 0.367%

    No Known Activations