© 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. 9-LLAMASCOPE-RES-131K
    11. 95819
    Prev
    Next
    INDEX
    Explanations

    mentions of the brand "Lego"

    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
    Ùħار
    -0.06
    nt
    -0.06
    assa
    -0.06
    occo
    -0.06
    åı·
    -0.06
    |--------------------------------------------------------------------------↵
    -0.06
    fried
    -0.06
    istrovstvÃŃ
    -0.06
     Gate
    -0.06
    .fs
    -0.05
    POSITIVE LOGITS
    365
    0.07
    tober
    0.07
    gett
    0.07
     tvar
    0.07
    ÙĪÙħاÙĨ
    0.07
    éĿĴ
    0.07
    .xz
    0.06
    olah
    0.06
    eding
    0.06
    edom
    0.06
    Activations Density 0.001%

    No Known Activations