© 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. 41079
    Prev
    Next
    INDEX
    Explanations

    key phrases related to primary motivations or interests

    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
    irit
    -0.07
    ÐĵÐŀ
    -0.06
    ög
    -0.06
    olib
    -0.06
    ogui
    -0.06
    orton
    -0.06
    å»
    -0.06
    pected
    -0.06
    udit
    -0.06
    Ñĥд
    -0.06
    POSITIVE LOGITS
     aim
    0.09
     goal
    0.09
     concern
    0.08
     ÑĨелÑĮ
    0.07
     job
    0.07
     objective
    0.07
     concerns
    0.07
     collabor
    0.07
    objective
    0.07
     brushes
    0.07
    Activations Density 0.022%

    No Known Activations