© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 120750
    Prev
    Next
    INDEX
    Explanations

    discussions about the importance and impact of the internet

    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
    hips
    -0.08
    μι
    -0.06
    arest
    -0.06
     Hospitality
    -0.06
    zing
    -0.06
    Aspect
    -0.06
    eses
    -0.06
    fort
    -0.06
     Ef
    -0.06
     CFO
    -0.06
    POSITIVE LOGITS
    arti
    0.07
    iegel
    0.07
    porn
    0.07
    SCII
    0.07
    aÅĻ
    0.06
    ẹn
    0.06
     itself
    0.06
    Truthy
    0.06
    uppe
    0.06
    /mobile
    0.06
    Activations Density 0.015%

    No Known Activations