© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 120066
    Prev
    Next
    INDEX
    Explanations

    topics related to entertainment and media systems

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

    Text segments that appear to be titles or headlines for online content, often showing up after a paragraph break and before another content section. These tend to be followed by additional related text that elaborates on the topic introduced in the title.

    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
    _Static
    -0.07
    /*č↵
    -0.07
    _$_
    -0.07
     gridColumn
    -0.07
    .MixedReality
    -0.07
    оÑĤе
    -0.07
    ibre
    -0.06
    ÇIJ
    -0.06
    ẻ
    -0.06
    borg
    -0.06
    POSITIVE LOGITS
    hek
    0.06
    ince
    0.06
    TOTYPE
    0.06
    illon
    0.06
     Fs
    0.06
    nock
    0.05
    ÑĢÑĥÑĩ
    0.05
     Asp
    0.05
    bie
    0.05
     án
    0.05
    Activations Density 0.127%

    No Known Activations