© 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. 56057
    Prev
    Next
    INDEX
    Explanations

    relationships and dependencies among various scientific factors and conditions

    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
    orz
    -0.06
     Tomb
    -0.06
    nist
    -0.06
    zk
    -0.06
     dele
    -0.06
     pains
    -0.06
    earch
    -0.05
     wor
    -0.05
    åı·
    -0.05
     Bel
    -0.05
    POSITIVE LOGITS
     depends
    0.15
     depend
    0.14
    depends
    0.14
     завиÑģиÑĤ
    0.12
     Depends
    0.12
     depending
    0.11
     depended
    0.11
     determined
    0.11
    depending
    0.10
     dependent
    0.10
    Activations Density 0.040%

    No Known Activations