© 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. 130502
    Prev
    Next
    INDEX
    Explanations

    special formatting or stylistic elements in the text

    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
    imd
    -0.09
    aviours
    -0.07
    ácil
    -0.07
     desar
    -0.07
    anvas
    -0.07
    culos
    -0.07
    æ°ı
    -0.06
     Ñĥмов
    -0.06
    earch
    -0.06
    ообÑĢаз
    -0.06
    POSITIVE LOGITS
    ific
    0.07
    Checkpoint
    0.06
     related
    0.06
    ãģŁãĤī
    0.06
     themed
    0.06
    æļ
    0.06
    ëĭ¤ëĬĶ
    0.06
     zoekt
    0.06
     Guth
    0.05
     alike
    0.05
    Activations Density 0.045%

    No Known Activations