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

    Neuronpedia

    Jacobian LensNEW
    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. 76542
    Prev
    Next
    INDEX
    Explanations

    temporal phrases related to events occurring in a sequence

    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
    AMED
    -0.08
    oÅĻ
    -0.08
     ساÙĦÙĩ
    -0.07
    .listBox
    -0.07
    ês
    -0.07
    宾
    -0.07
    licate
    -0.06
    ose
    -0.06
    ushman
    -0.06
    覧
    -0.06
    POSITIVE LOGITS
     rival
    0.06
    uten
    0.06
    arte
    0.06
    integral
    0.06
    ubre
    0.06
    APT
    0.06
    imuth
    0.05
     mark
    0.05
    'er
    0.05
     Leather
    0.05
    Activations Density 0.007%

    No Known Activations