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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 57696
    Prev
    Next
    INDEX
    Explanations

    instances of reasoning or justification in thought processes

    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
    voje
    -0.07
    bourg
    -0.07
    å®ļçļĦ
    -0.07
    _CB
    -0.06
     typealias
    -0.06
     Basics
    -0.06
    rier
    -0.06
    quare
    -0.06
    buat
    -0.06
    keh
    -0.06
    POSITIVE LOGITS
     ways
    0.14
     how
    0.11
     Ways
    0.11
     list
    0.09
     reasons
    0.08
     lists
    0.07
     cómo
    0.07
    åIJĦç§į
    0.07
    ómo
    0.07
    å¦Ĥä½ķ
    0.07
    Activations Density 0.063%

    No Known Activations