© 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. 81627
    Prev
    Next
    INDEX
    Explanations

    technical terms and measurements related to construction and plumbing systems

    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
    ynchronously
    -0.07
    strand
    -0.07
     envelope
    -0.06
     ropes
    -0.06
     envelopes
    -0.06
     å¾Ĵ
    -0.06
    沿
    -0.06
     avenue
    -0.06
     continuum
    -0.06
    iero
    -0.06
    POSITIVE LOGITS
     junction
    0.10
     góc
    0.09
    junction
    0.09
     bend
    0.09
     corners
    0.09
    fork
    0.09
     bends
    0.09
    OTO
    0.09
     corner
    0.08
     jun
    0.08
    Activations Density 0.069%

    No Known Activations