© 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. 74610
    Prev
    Next
    INDEX
    Explanations

    references to iconic comedians and their performances

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

    Names of people, places, and other proper nouns that are frequently mentioned in biographical or informational content, with particular emphasis on entertainment figures.

    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
    /Branch
    -0.08
    URLException
    -0.08
    ieder
    -0.07
    Fcn
    -0.07
    -Identifier
    -0.07
    /Set
    -0.07
    kJ
    -0.07
    mbH
    -0.07
     Tarif
    -0.07
    -Regular
    -0.07
    POSITIVE LOGITS
    brtc
    0.07
    DataGridViewTextBoxColumn
    0.06
     iii
    0.06
     provid
    0.06
    ï¼
    0.06
     c
    0.06
    ToolStripMenuItem
    0.06
    ži
    0.06
    -lg
    0.06
     ve
    0.06
    Activations Density 0.819%

    No Known Activations