© 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. 15-LLAMASCOPE-RES-131K
    11. 87143
    Prev
    Next
    INDEX
    Explanations

    special character sequences and formatting in structured text or code

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

    Special syntax characters that serve specific functions in programming languages, markup, mathematical notation, or document formatting.

    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
    er
    -0.16
    a
    -0.14
    ãģĦãĤĭ
    -0.13
    e
    -0.13
    ãĥ£
    -0.12
    o
    -0.12
    ãĤ§
    -0.11
    i
    -0.11
    en
    -0.11
    ed
    -0.11
    POSITIVE LOGITS
    inition
    0.10
    bsite
    0.10
    ategy
    0.10
    tempts
    0.10
    ergency
    0.09
    ments
    0.09
    enticate
    0.09
    ftware
    0.09
    autiful
    0.09
    otros
    0.08
    Activations Density 0.207%

    No Known Activations