© 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. 61745
    Prev
    Next
    INDEX
    Explanations

    topics and categories related to technology and news

    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
    â̦â̦ãĢĤ
    -0.07
    lec
    -0.07
    amac
    -0.07
    çĽijåIJ¬é¡µéĿ¢
    -0.06
    atron
    -0.06
    ibir
    -0.06
    .Av
    -0.06
    _dyn
    -0.06
     Anonymous
    -0.06
    â̦"↵↵
    -0.06
    POSITIVE LOGITS
    -news
    0.08
    à¸Ħว
    0.07
    News
    0.07
     news
    0.06
     espa
    0.06
    .news
    0.06
    news
    0.06
    akis
    0.06
    .habbo
    0.06
     Uncategorized
    0.06
    Activations Density 0.002%

    No Known Activations