© 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. 75927
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and event dates

    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
     germ
    -0.07
    akat
    -0.06
     Trio
    -0.06
    asma
    -0.06
     Dial
    -0.06
     tele
    -0.06
     ob
    -0.05
     Advent
    -0.05
     Liber
    -0.05
    rael
    -0.05
    POSITIVE LOGITS
    (disposing
    0.07
    Aceptar
    0.07
     noreferrer
    0.07
    SCP
    0.07
     Rosenberg
    0.07
    yster
    0.07
    Scalars
    0.06
    Pg
    0.06
    loquent
    0.06
    常
    0.06
    Activations Density 0.005%

    No Known Activations