© 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. 55264
    Prev
    Next
    INDEX
    Explanations

    structured programming code and related elements

    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
    ikan
    -0.09
    hiro
    -0.07
    kan
    -0.07
    overn
    -0.06
    åĿĤ
    -0.06
    880
    -0.06
    logan
    -0.06
    itez
    -0.06
    itsu
    -0.06
    erness
    -0.06
    POSITIVE LOGITS
    ust
    0.06
    OnInit
    0.06
    aru
    0.06
    tpl
    0.06
    ensible
    0.06
    ãĥĩãĥ«
    0.06
    agine
    0.06
    uru
    0.06
     quiet
    0.06
    dist
    0.06
    Activations Density 0.014%

    No Known Activations