© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 128849
    Prev
    Next
    INDEX
    Explanations

    historical references to conflicts or wars

    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
    tone
    -0.06
    hlen
    -0.06
    PFN
    -0.06
     Grim
    -0.05
     oldValue
    -0.05
    ception
    -0.05
    stitution
    -0.05
    inline
    -0.05
     propagation
    -0.05
    ÑĤÑĶ
    -0.05
    POSITIVE LOGITS
    åĿĤ
    0.07
     è¾ĵ
    0.07
     diplom
    0.07
    ë²Į
    0.07
    adera
    0.07
    .ag
    0.07
    âĢĮâĢĮ
    0.07
    _TAC
    0.07
    Ĺ
    0.07
    âĺĨ
    0.07
    Activations Density 0.045%

    No Known Activations