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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 88540
    Prev
    Next
    INDEX
    Explanations

    questions and prompts that seek to identify or describe important aspects of situations, often involving comparisons or evaluations

    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
    lier
    -0.07
     Cop
    -0.07
     meisten
    -0.06
    ñ
    -0.06
    tron
    -0.06
    ulk
    -0.06
    ets
    -0.06
    ãĥ³ãĥ
    -0.06
    ợ
    -0.06
    kop
    -0.06
    POSITIVE LOGITS
    å±ĭ
    0.07
     evidence
    0.07
     difference
    0.07
    686
    0.06
    enaire
    0.06
     exactly
    0.06
     significance
    0.06
    ilden
    0.06
     Evidence
    0.06
    akah
    0.06
    Activations Density 0.014%

    No Known Activations