Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 83016
    Prev
    Next
    INDEX
    Explanations

    elements related to webpage structure and content management

    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
    ansi
    -0.07
    strand
    -0.07
    egas
    -0.06
     dál
    -0.06
    ditor
    -0.06
    ythe
    -0.06
    umni
    -0.06
    awner
    -0.06
    rane
    -0.06
    anut
    -0.06
    POSITIVE LOGITS
     Hlav
    0.07
    .synthetic
    0.06
    ":[{↵
    0.06
    scripts
    0.06
     DISCLAIM
    0.06
     Ad
    0.06
     cao
    0.06
    ANTE
    0.06
    cript
    0.06
     Collector
    0.06
    Activations Density 0.003%

    No Known Activations