© 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. 15667
    Prev
    Next
    INDEX
    Explanations

    mentions of Iran and its related terms

    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
    ering
    -0.08
    y
    -0.07
     بÙĪابة
    -0.07
    ed
    -0.07
    gle
    -0.07
    yor
    -0.07
    552
    -0.06
    cz
    -0.06
    acon
    -0.06
    ev
    -0.06
    POSITIVE LOGITS
    ateg
    0.09
    ophobia
    0.08
    (IR
    0.08
    neau
    0.07
    CELL
    0.07
    imed
    0.07
    ious
    0.07
    ucle
    0.07
    udge
    0.07
    ÄįÃŃ
    0.07
    Activations Density 0.011%

    No Known Activations