© 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. 107336
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially names and titles associated with individuals and entities

    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
    parator
    -0.08
    NgModule
    -0.07
    reate
    -0.07
    ạm
    -0.07
    ÄĽr
    -0.07
    кÑĥÑĢ
    -0.06
    Å¡k
    -0.06
    AZY
    -0.06
    ookies
    -0.06
    clus
    -0.06
    POSITIVE LOGITS
     seedu
    0.06
    engu
    0.06
    adi
    0.06
     Rever
    0.06
    -valu
    0.06
    portun
    0.05
    иÑı
    0.05
    068
    0.05
    ’
    0.05
    аÑĤкÑĥ
    0.05
    Activations Density 0.014%

    No Known Activations