© 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. 78589
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and expressions, particularly those involving differentials and deltas

    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
    ifar
    -0.07
    ands
    -0.06
    entric
    -0.06
    ugi
    -0.06
     Tal
    -0.06
    isor
    -0.06
     Parties
    -0.06
    aylight
    -0.06
    >{"
    -0.06
    ondo
    -0.06
    POSITIVE LOGITS
    åIJ
    0.06
    ount
    0.06
    ESTAMP
    0.06
    les
    0.06
    rát
    0.06
    387
    0.06
     Lump
    0.05
    ets
    0.05
    ative
    0.05
     synthesis
    0.05
    Activations Density 0.113%

    No Known Activations