© 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. 86730
    Prev
    Next
    INDEX
    Explanations

    references to communication through letters and correspondence

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

    References to written correspondence, primarily letters being sent, received, or exchanged between people, often including mentions of the sender, recipient, or content of the communication.

    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
     rolled
    -0.07
     Rolled
    -0.06
     walk
    -0.06
     roll
    -0.06
    alse
    -0.06
    entr
    -0.05
    orsk
    -0.05
    æĹĹ
    -0.05
     ret
    -0.05
    661
    -0.05
    POSITIVE LOGITS
     letter
    0.09
     letters
    0.09
     LETTER
    0.09
     addressed
    0.09
    Charsets
    0.08
    -letter
    0.08
     Letter
    0.08
     Letters
    0.08
    letter
    0.08
    letters
    0.08
    Activations Density 0.040%

    No Known Activations