© 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. 15-LLAMASCOPE-RES-131K
    11. 90528
    Prev
    Next
    INDEX
    Explanations

    terms related to measurements and scientific variables

    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
    ardy
    -0.06
    oad
    -0.06
    ilton
    -0.06
     a
    -0.06
     pars
    -0.06
    úsqueda
    -0.05
    ç½²
    -0.05
    time
    -0.05
    oky
    -0.05
    301
    -0.05
    POSITIVE LOGITS
     particle
    0.09
    particles
    0.08
     particles
    0.08
    çŃ
    0.08
     sie
    0.08
    particle
    0.08
     Particle
    0.08
    Particle
    0.07
    Particles
    0.07
    .bits
    0.07
    Activations Density 0.012%

    No Known Activations