© 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. 55993
    Prev
    Next
    INDEX
    Explanations

    concepts related to linear subspaces and their dimensions

    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
    ahun
    -0.07
    qu
    -0.07
    amac
    -0.06
    cka
    -0.06
    quia
    -0.06
    à¥ģà¤
    -0.06
    utta
    -0.06
    ijk
    -0.06
    undle
    -0.06
     chords
    -0.06
    POSITIVE LOGITS
     each
    0.13
    åIJĦ
    0.13
    each
    0.12
     åIJĦ
    0.12
    (each
    0.11
     ê°ģê°ģ
    0.11
     EACH
    0.11
    .each
    0.11
     cada
    0.10
     Each
    0.10
    Activations Density 0.201%

    No Known Activations