© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 75934
    Prev
    Next
    INDEX
    Explanations

    expressions of personal effort and achievement

    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
    oidal
    -0.07
    anki
    -0.07
    anz
    -0.07
    aul
    -0.06
     byt
    -0.06
    oser
    -0.06
    ndern
    -0.06
    ospace
    -0.06
    .tem
    -0.06
     Cruc
    -0.06
    POSITIVE LOGITS
    å°½
    0.08
     correctly
    0.08
    æľĢä½³
    0.08
     properly
    0.08
     correct
    0.08
     maxim
    0.08
     maximal
    0.08
    æŃ£ç¡®
    0.07
    ayne
    0.07
     fully
    0.07
    Activations Density 0.026%

    No Known Activations