© 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. 55880
    Prev
    Next
    INDEX
    Explanations

    numerical dimensions and measurements, particularly in relation to clothing sizes or physical dimensions

    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
    nete
    -0.07
    noinspection
    -0.06
     Webster
    -0.06
    antas
    -0.06
     nd
    -0.06
     tion
    -0.05
    verse
    -0.05
     immersed
    -0.05
    lord
    -0.05
    lector
    -0.05
    POSITIVE LOGITS
    isses
    0.07
    alg
    0.07
    issen
    0.07
     ãģĿãģ®ä»ĸ
    0.07
    prung
    0.07
    omm
    0.07
    iÃŁ
    0.06
    alex
    0.06
    upp
    0.06
    ahun
    0.06
    Activations Density 0.006%

    No Known Activations