© 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. 126476
    Prev
    Next
    INDEX
    Explanations

    phrases related to writing or recording information

    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
    akh
    -0.10
    awk
    -0.06
    ivent
    -0.05
    coma
    -0.05
    Äĥr
    -0.05
    alk
    -0.05
    QA
    -0.05
    ekl
    -0.05
     Pes
    -0.05
    -par
    -0.05
    POSITIVE LOGITS
    ÑĤеÑĢн
    0.08
    .scalablytyped
    0.07
    arius
    0.07
    ãģ£ãģį
    0.07
    ãĥ¼ãĤ¹ãĥĪ
    0.07
    DownList
    0.07
    ุส
    0.07
     Hayward
    0.07
     onto
    0.07
    -ни
    0.07
    Activations Density 0.009%

    No Known Activations