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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 256
    Prev
    Next
    INDEX
    Explanations

    metaphorical language related to connection and support

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

    Concrete nouns used metaphorically to describe how one concept facilitates, connects, or enables another concept.

    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
    iga
    -0.07
    kir
    -0.07
    agar
    -0.06
    leck
    -0.06
    igs
    -0.06
    æŁ³
    -0.06
    IDD
    -0.06
     PLEASE
    -0.06
    berger
    -0.06
    AGR
    -0.06
    POSITIVE LOGITS
     bagi
    0.09
     for
    0.09
     длÑı
    0.08
     facto
    0.07
    activex
    0.07
    ÃĵN
    0.07
     Dive
    0.07
    /WebAPI
    0.07
    _Tis
    0.07
    .scalablytyped
    0.07
    Activations Density 0.031%

    No Known Activations