© 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. 126881
    Prev
    Next
    INDEX
    Explanations

    concepts related to symmetry in nuclear physics

    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
    MEA
    -0.07
    éģ
    -0.07
    .setViewport
    -0.07
    \Id
    -0.07
    eyn
    -0.07
    ÑĢай
    -0.06
    rze
    -0.06
    OME
    -0.06
    anzeigen
    -0.06
    .accounts
    -0.06
    POSITIVE LOGITS
     symmetry
    0.14
     sym
    0.10
    sym
    0.09
     structure
    0.07
    _sym
    0.07
    Sym
    0.07
    .sym
    0.07
     Sym
    0.07
     crystal
    0.07
     disorder
    0.07
    Activations Density 0.063%

    No Known Activations