© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 77351
    Prev
    Next
    INDEX
    Explanations

    concepts related to measurement and evaluation of conditions or qualities

    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
    tat
    -0.07
    tout
    -0.07
     arrayWith
    -0.07
    ndl
    -0.07
    arie
    -0.07
    elib
    -0.07
    kir
    -0.07
    ettle
    -0.07
    Ïĥί
    -0.07
    DOMNode
    -0.07
    POSITIVE LOGITS
     nÃło
    0.09
     degree
    0.08
     SOME
    0.07
     olsa
    0.07
     decent
    0.07
     atleast
    0.07
     reasonably
    0.07
     sembl
    0.07
     semi
    0.06
     Fu
    0.06
    Activations Density 0.028%

    No Known Activations