© 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. 77810
    Prev
    Next
    INDEX
    Explanations

    indicatives of online post attributes or metadata

    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
    agon
    -0.06
     Kush
    -0.06
    sten
    -0.06
    ONEY
    -0.06
     Pis
    -0.06
    oya
    -0.05
    اة
    -0.05
    atis
    -0.05
    éŀ
    -0.05
    asi
    -0.05
    POSITIVE LOGITS
    ubre
    0.07
    UInteger
    0.07
    á»ijng
    0.07
    dre
    0.07
    antha
    0.07
    éĽĦ
    0.07
    ustomed
    0.06
    λί
    0.06
     apro
    0.06
    Äįka
    0.06
    Activations Density 0.000%

    No Known Activations