© 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. 118362
    Prev
    Next
    INDEX
    Explanations

    programming constructs and mathematical functions related to kinematics

    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
    PEAT
    -0.07
    μη
    -0.07
    wich
    -0.06
     ÑĢеÑģ
    -0.06
     atomic
    -0.06
     Ear
    -0.06
    eldo
    -0.06
    chez
    -0.06
     Atomic
    -0.06
     twe
    -0.06
    POSITIVE LOGITS
     Motion
    0.09
     robot
    0.08
     motion
    0.08
     kin
    0.08
     motor
    0.08
    Robot
    0.08
     motors
    0.08
     humanoid
    0.08
     Robot
    0.08
    Motion
    0.08
    Activations Density 0.092%

    No Known Activations