© 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. 3639
    Prev
    Next
    INDEX
    Explanations

    concepts related to trial and error learning

    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
    sher
    -0.07
    itat
    -0.07
    onica
    -0.06
    ilir
    -0.06
    ÑĮеÑĢ
    -0.06
    asca
    -0.06
    IMIZE
    -0.06
    .lesson
    -0.06
    âu
    -0.06
    orest
    -0.06
    POSITIVE LOGITS
     alone
    0.11
     Alone
    0.11
     rather
    0.10
    alone
    0.08
    rather
    0.08
    -Based
    0.08
    -alone
    0.07
    -based
    0.07
     Rather
    0.07
    629
    0.07
    Activations Density 0.039%

    No Known Activations