© 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. 129340
    Prev
    Next
    INDEX
    Explanations

    programmatic logic checks related to constraints

    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
    PÅĻÃŃ
    -0.06
    icus
    -0.06
    iph
    -0.06
    aspers
    -0.06
    elles
    -0.06
    iqu
    -0.06
    ificial
    -0.06
    pte
    -0.06
    .interfaces
    -0.06
    orny
    -0.06
    POSITIVE LOGITS
    ioned
    0.07
    wing
    0.07
    ailer
    0.07
    ited
    0.07
    kir
    0.06
     Lange
    0.06
    Ñĥвали
    0.06
    iÄįky
    0.06
     Sof
    0.06
     zero
    0.06
    Activations Density 0.017%

    No Known Activations