© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 86126
    Prev
    Next
    INDEX
    Explanations

    concepts and ideas related to business developments or plans

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Text describing ideas, plans, concepts or proposals, often in the context of collaborative development or initial formation stages of projects.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219
    Triggered by @lu-christina
    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
    Negative Logits
    esa
    -0.08
    ilis
    -0.07
    itr
    -0.07
    xies
    -0.06
    arnings
    -0.06
    ogy
    -0.06
    erah
    -0.06
    ifdef
    -0.06
    xes
    -0.06
    å½
    -0.06
    POSITIVE LOGITS
     idea
    0.13
     ideas
    0.13
     Idea
    0.12
    ideas
    0.11
     Ideas
    0.11
    idea
    0.11
     proposal
    0.10
     concept
    0.09
     plan
    0.09
     project
    0.09
    Activations Density 0.136%

    No Known Activations