© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 82280
    Prev
    Next
    INDEX
    Explanations

    instances of the word “never” in various contexts

    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
    ãĥĨãĥ«
    -0.07
    еÑĩно
    -0.07
    ardu
    -0.07
    ÙĦÙĪد
    -0.07
    asurer
    -0.06
    untu
    -0.06
    жа
    -0.06
    Ế
    -0.06
    ä¸ĸç´Ģ
    -0.06
    instanc
    -0.06
    POSITIVE LOGITS
    inka
    0.06
     intent
    0.06
     fully
    0.06
    -ending
    0.06
     intended
    0.06
    never
    0.06
    theless
    0.06
    ursal
    0.06
    AVA
    0.06
    uthor
    0.06
    Activations Density 0.022%

    No Known Activations