© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 82426
    Prev
    Next
    INDEX
    Explanations

    phrases encouraging exploration and discovery of information or content

    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
    ÌĪ
    -0.07
    eteor
    -0.06
    deen
    -0.06
    itunes
    -0.06
    tos
    -0.06
    åİħ
    -0.05
    fte
    -0.05
    azard
    -0.05
     irgend
    -0.05
    hunt
    -0.05
    POSITIVE LOGITS
     details
    0.10
    details
    0.09
    DETAIL
    0.08
     DETAILS
    0.08
     detalles
    0.08
    详
    0.08
    Details
    0.08
     learn
    0.07
    844
    0.07
    -details
    0.07
    Activations Density 0.022%

    No Known Activations