© 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. 17248
    Prev
    Next
    INDEX
    Explanations

    words related to specific products or brands

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

    The character sequences "um" and "am" appearing within words across various languages and contexts, including names, technical terms, and regular vocabulary.

    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
    p
    -0.12
    pom
    -0.10
    b
    -0.09
    odox
    -0.08
    pic
    -0.08
    âĶģâĶģ
    -0.08
    pz
    -0.08
    pri
    -0.08
    àµį
    -0.08
    pw
    -0.08
    POSITIVE LOGITS
    atically
    0.12
    oltip
    0.10
    ming
    0.09
    ìį¨
    0.09
    azing
    0.09
    pton
    0.08
    ichael
    0.08
    olecular
    0.08
    nesty
    0.08
    essenger
    0.08
    Activations Density 1.132%

    No Known Activations