© 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. 117977
    Prev
    Next
    INDEX
    Explanations

    instances of declarative speech and quotation

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

    Speech attribution markers that introduce quotations or reported speech, including verbs like "say" and punctuation like colons followed by quotation marks.

    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
    okit
    -0.07
    -et
    -0.07
    ειο
    -0.06
    ino
    -0.06
    anos
    -0.06
     Zum
    -0.06
    ÑĦа
    -0.06
     Bits
    -0.06
    å¼¾
    -0.06
    åŀĤ
    -0.06
    POSITIVE LOGITS
    ptic
    0.07
    deer
    0.06
    pery
    0.06
    atta
    0.06
    bersome
    0.06
    /Framework
    0.06
    lisi
    0.06
    geist
    0.06
    åĵ
    0.06
    kees
    0.06
    Activations Density 0.033%

    No Known Activations