© 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. 123851
    Prev
    Next
    INDEX
    Explanations

    detailed procedural descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens that introduce or describe a process, methodology, or structural organization within instructional or explanatory text.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    .CG
    -0.07
    ilip
    -0.07
    rava
    -0.06
    eshire
    -0.06
     çľ
    -0.06
    reso
    -0.06
    عاÙĨ
    -0.06
    ause
    -0.06
     toolbox
    -0.06
    ãĤ¹ãĤ¯
    -0.06
    POSITIVE LOGITS
     typical
    0.12
     procedure
    0.11
     sequence
    0.11
     scenario
    0.11
     steps
    0.10
     Typical
    0.10
     workflow
    0.10
    typ
    0.10
    Typ
    0.10
     process
    0.09
    Activations Density 0.110%

    No Known Activations