© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 98705
    Prev
    Next
    INDEX
    Explanations

    sections and subtopics within academic or informative texts

    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
    vla
    -0.08
    訴
    -0.07
     mát
    -0.07
    даÑħ
    -0.07
    RID
    -0.07
    èĩ¨
    -0.07
    Mvc
    -0.07
    istros
    -0.06
    å¾
    -0.06
    elu
    -0.06
    POSITIVE LOGITS
    onica
    0.07
    319
    0.06
    IS
    0.06
    ase
    0.06
    cc
    0.06
    atters
    0.06
    kte
    0.06
    礼
    0.05
    ť
    0.05
    unda
    0.05
    Activations Density 0.008%

    No Known Activations