© 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. 31722
    Prev
    Next
    INDEX
    Explanations

    references to walls or wall-related concepts in various contexts

    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
    eka
    -0.08
    اÙĦس
    -0.07
    agli
    -0.07
    ideographic
    -0.07
    este
    -0.07
    emia
    -0.07
    esus
    -0.07
    ussen
    -0.07
    zelf
    -0.07
    edu
    -0.07
    POSITIVE LOGITS
    ington
    0.09
    abies
    0.08
    aver
    0.08
    flower
    0.08
    gren
    0.08
    entin
    0.08
    kommen
    0.07
    å£ģ
    0.07
    enstein
    0.07
    flowers
    0.07
    Activations Density 0.013%

    No Known Activations