© 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. 17-LLAMASCOPE-RES-131K
    11. 105287
    Prev
    Next
    INDEX
    Explanations

    specific nouns related to objects, concepts, or themes in technical or creative contexts

    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
    oser
    -0.08
    èĢ
    -0.07
    798
    -0.06
    aklı
    -0.06
     godt
    -0.06
    RR
    -0.06
    çıį
    -0.06
    icians
    -0.06
    ÑıÑĤно
    -0.06
    ebb
    -0.06
    POSITIVE LOGITS
     OTHERWISE
    0.08
     inorder
    0.07
     nhằm
    0.07
     thereby
    0.07
     Bes
    0.06
     böylece
    0.06
    以
    0.06
    ar
    0.06
    achen
    0.06
    162
    0.06
    Activations Density 0.067%

    No Known Activations