© 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. 79627
    Prev
    Next
    INDEX
    Explanations

    phrases related to events, participation, and inclusivity in a community context

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

    Common formatting and syntax elements that serve as connectors or delimiters in code, HTML, or text content.

    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
    lotte
    -0.07
    aptive
    -0.06
    олÑı
    -0.06
    renc
    -0.06
    Į
    -0.06
    tility
    -0.06
    umb
    -0.06
    UMB
    -0.06
    ħĮ
    -0.06
    ilio
    -0.06
    POSITIVE LOGITS
    ÃĹ↵↵
    0.08
    ãĥ¼ãĥĭ
    0.06
    oir
    0.06
    enga
    0.06
    ando
    0.06
     pct
    0.06
    wk
    0.05
    bes
    0.05
     Byrne
    0.05
     Mü
    0.05
    Activations Density 0.376%

    No Known Activations