© 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. 128727
    Prev
    Next
    INDEX
    Explanations

    punctuations or symbols that are commonly used in technical documents and specifications

    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
    ourg
    -0.08
    stroy
    -0.07
    мон
    -0.07
    azen
    -0.07
    &o
    -0.07
    поÑĩ
    -0.07
    oley
    -0.06
     profil
    -0.06
    (PHP
    -0.06
    wald
    -0.06
    POSITIVE LOGITS
    umes
    0.07
     Officers
    0.07
    strap
    0.07
     Officer
    0.07
    íķ
    0.06
     Cooperative
    0.06
    REEN
    0.06
     officer
    0.06
    ед
    0.06
    icios
    0.06
    Activations Density 0.000%

    No Known Activations