© 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. 9-LLAMASCOPE-RES-131K
    11. 94196
    Prev
    Next
    INDEX
    Explanations

    statements related to product quality and delivery details

    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
     itself
    -0.08
    ist
    -0.07
     Sil
    -0.06
     himself
    -0.06
     ent
    -0.06
     Sharon
    -0.06
     par
    -0.06
     procedure
    -0.05
     She
    -0.05
    ep
    -0.05
    POSITIVE LOGITS
    айд
    0.08
    contres
    0.08
     ogl
    0.08
    .COLOR
    0.07
    ahun
    0.07
    hiba
    0.07
    ÃĹ↵↵
    0.07
    rowser
    0.07
    ĮĢ
    0.07
    iyan
    0.07
    Activations Density 0.029%

    No Known Activations