© 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 EvalsExportsAPI 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. 16431
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and indicators of excitement or emphasis

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

    End points of distinct content sections or information blocks, often preceding a transition to a new topic.

    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
     also
    -0.07
    quia
    -0.07
    izr
    -0.06
     indeed
    -0.06
     thereby
    -0.06
    atak
    -0.06
     then
    -0.06
     other
    -0.06
     дÑĢÑĥгие
    -0.06
    άÏĥ
    -0.06
    POSITIVE LOGITS
    OPSIS
    0.08
    hattan
    0.07
    odore
    0.07
    _Lean
    0.06
     Boulevard
    0.06
    rientation
    0.06
    okers
    0.06
    Util
    0.06
    IGIN
    0.06
    soever
    0.06
    Activations Density 0.003%

    No Known Activations