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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29015
    Prev
    Next
    INDEX
    Explanations

    technical documentation and configuration settings related to software installations

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    åį
    -0.07
    ween
    -0.06
    eniable
    -0.06
     dest
    -0.06
    èķ
    -0.06
     Ranking
    -0.06
    .xhtml
    -0.06
    FontAwesomeIcon
    -0.06
    ieces
    -0.06
    еÑĪ
    -0.05
    POSITIVE LOGITS
    .workspace
    0.07
    .jetbrains
    0.07
     Grad
    0.06
    fromJson
    0.06
    igram
    0.06
     Gerr
    0.06
    .gradle
    0.06
     regional
    0.06
     Tob
    0.06
    ÑĽ
    0.06
    Activations Density 0.013%

    No Known Activations