© 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. 128521
    Prev
    Next
    INDEX
    Explanations

    parenthetical phrases and their associated commentary

    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
    .TypeOf
    -0.07
    ällt
    -0.07
    âĢ¦âĢ¦ãĢĤ
    -0.07
    èµı
    -0.06
    :CGRect
    -0.06
    ео
    -0.06
    impan
    -0.06
    worthy
    -0.06
    rapped
    -0.06
    寸
    -0.06
    POSITIVE LOGITS
     adel
    0.06
     forn
    0.06
    ino
    0.06
     now
    0.06
     escorte
    0.06
    makta
    0.05
    adia
    0.05
    orf
    0.05
    lope
    0.05
     increasingly
    0.05
    Activations Density 0.041%

    No Known Activations