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. 118735
    Prev
    Next
    INDEX
    Explanations

    references to VPN functionality and its benefits

    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
    izontal
    -0.07
    .LookAndFeel
    -0.07
    odon
    -0.07
    icari
    -0.07
    gan
    -0.07
     Landing
    -0.07
    -await
    -0.07
    icont
    -0.07
    bury
    -0.07
    SqlParameter
    -0.07
    POSITIVE LOGITS
    HQ
    0.08
     HQ
    0.07
    ả
    0.07
    aÅŁ
    0.06
     layer
    0.06
    asons
    0.06
     anonymity
    0.06
    orgia
    0.06
     layers
    0.06
     Layer
    0.06
    Activations Density 0.013%

    No Known Activations