© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 119977
    Prev
    Next
    INDEX
    Explanations

    instances of the letter sequence "u"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ức
    -0.08
    zym
    -0.07
    emie
    -0.07
    pcm
    -0.07
    aning
    -0.07
    verted
    -0.07
    jal
    -0.07
    ff
    -0.07
    ipt
    -0.06
    Ñİ
    -0.06
    POSITIVE LOGITS
    s
    0.08
    eto
    0.06
    alse
    0.06
     Stevenson
    0.06
    dash
    0.06
     Nug
    0.06
    η
    0.06
    224
    0.06
    tip
    0.06
    20
    0.06
    Activations Density 0.011%

    No Known Activations