© 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. 1628
    Prev
    Next
    INDEX
    Explanations

    terminology related to machinery and engineering

    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
     Fauc
    -0.07
    ãģĭãģij
    -0.07
    ddy
    -0.07
    andelier
    -0.07
    rypton
    -0.07
    RAFT
    -0.07
    nila
    -0.06
    -gun
    -0.06
    foil
    -0.06
     Warfare
    -0.06
    POSITIVE LOGITS
     crushing
    0.08
     Crush
    0.08
     Crushers
    0.08
     rock
    0.07
     operator
    0.07
     mobile
    0.07
     Crushing
    0.07
     crush
    0.07
     Crusher
    0.07
     crusher
    0.07
    Activations Density 0.017%

    No Known Activations