© 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. 69216
    Prev
    Next
    INDEX
    Explanations

    CSS style rules and positioning properties related to web design layout

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    udas
    -0.07
     Floors
    -0.06
    !=(
    -0.06
    IA
    -0.06
    apg
    -0.06
     Noon
    -0.06
     floors
    -0.06
    sex
    -0.05
    iven
    -0.05
     composition
    -0.05
    POSITIVE LOGITS
    abet
    0.07
    ottom
    0.07
     UNIVERS
    0.07
     Credential
    0.07
    enschaft
    0.07
     Binder
    0.07
    .scalablytyped
    0.07
     Bart
    0.07
    aisy
    0.06
    longleftrightarrow
    0.06
    Activations Density 0.004%

    No Known Activations