© 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. 72977
    Prev
    Next
    INDEX
    Explanations

    technical terms related to astrophysics and the motion of celestial bodies

    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
    urum
    -0.07
    OTS
    -0.07
    urf
    -0.07
    peaker
    -0.07
     Dal
    -0.06
    Serialized
    -0.06
     Uz
    -0.06
    arus
    -0.06
    krom
    -0.06
    ridor
    -0.06
    POSITIVE LOGITS
     moving
    0.08
     motion
    0.08
     movement
    0.08
     move
    0.08
     relative
    0.07
     Motion
    0.07
    motion
    0.07
     дви
    0.07
    -moving
    0.07
     mot
    0.07
    Activations Density 0.029%

    No Known Activations