© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 127611
    Prev
    Next
    INDEX
    Explanations

    copyright and licensing terms related to images and content

    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
    eras
    -0.08
    aac
    -0.07
    inki
    -0.07
    foy
    -0.07
    ingly
    -0.07
    esel
    -0.07
    ä¸ĺ
    -0.06
    AsyncResult
    -0.06
     pij
    -0.06
    ombo
    -0.06
    POSITIVE LOGITS
    аг
    0.07
    tered
    0.07
    856
    0.06
    894
    0.06
    ÏĦικα
    0.06
    à¥įपर
    0.06
    á
    0.05
    iero
    0.05
     Reconstruction
    0.05
    -serif
    0.05
    Activations Density 0.001%

    No Known Activations