© 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. 17055
    Prev
    Next
    INDEX
    Explanations

    programming language import statements

    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
     tac
    -0.07
    acho
    -0.06
    ayo
    -0.06
    \xa
    -0.06
    è´
    -0.06
    aye
    -0.06
    ayed
    -0.06
    arez
    -0.06
    bine
    -0.06
    SYNC
    -0.05
    POSITIVE LOGITS
    unto
    0.08
    ifr
    0.08
    ders
    0.07
    ERICA
    0.07
    inho
    0.07
     msgstr
    0.07
    ÙĪاء
    0.06
    hta
    0.06
    ngrx
    0.06
     onHide
    0.06
    Activations Density 0.008%

    No Known Activations