© 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. 126874
    Prev
    Next
    INDEX
    Explanations

    phrases related to availability and service hours, particularly in a 24/7 context

    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
    öt
    -0.08
    ordion
    -0.08
    озна
    -0.08
    ãĥªãĥ¼ãĤº
    -0.08
    ffa
    -0.08
    دÙĪد
    -0.08
     PROCUREMENT
    -0.08
    ghi
    -0.07
    uyên
    -0.07
    нина
    -0.07
    POSITIVE LOGITS
     Hind
    0.07
    anchor
    0.06
     Dump
    0.06
    abra
    0.06
     dumped
    0.06
    Interop
    0.05
    ilig
    0.05
    presence
    0.05
    yx
    0.05
     inf
    0.05
    Activations Density 0.002%

    No Known Activations