© 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. 82977
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with statistical data or measurements

    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
    inal
    -0.08
    inally
    -0.08
    alleries
    -0.08
    INAL
    -0.07
    nut
    -0.07
    ochen
    -0.07
    iness
    -0.07
    ream
    -0.07
    595
    -0.07
    guards
    -0.07
    POSITIVE LOGITS
    nd
    0.07
    th
    0.07
    ãĥ«ãĥĪ
    0.06
    ä¸ĸç´Ģ
    0.06
    ADER
    0.06
     Vision
    0.06
    nger
    0.06
     gang
    0.06
    ision
    0.06
    .metamodel
    0.06
    Activations Density 0.113%

    No Known Activations