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

    Neuronpedia

    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. 82219
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks and structural elements in mathematical expressions

    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
    ing
    -0.09
    edom
    -0.08
    >NN
    -0.08
    iag
    -0.07
    ablish
    -0.07
    chw
    -0.07
    ovu
    -0.07
     kvin
    -0.07
     HÃł
    -0.07
    utherland
    -0.07
    POSITIVE LOGITS
     ³³ ³³ ³³ ³³
    0.07
    ibar
    0.06
    assin
    0.06
    esters
    0.06
     singular
    0.06
    UNCH
    0.05
    arda
    0.05
    arer
    0.05
    obby
    0.05
    III
    0.05
    Activations Density 0.091%

    No Known Activations