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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 60668
    Prev
    Next
    INDEX
    Explanations

    references to historical conflicts and opposing sides in warfare

    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
    úng
    -0.07
    EMPL
    -0.07
    oha
    -0.06
    uu
    -0.06
    urv
    -0.06
    oft
    -0.06
    .gdx
    -0.06
    usch
    -0.06
    bp
    -0.06
     stor
    -0.06
    POSITIVE LOGITS
     miscellaneous
    0.07
     apolog
    0.07
    ÐļÐĺ
    0.06
     -*-č↵
    0.06
     Brave
    0.06
    BITS
    0.06
    atak
    0.06
    overview
    0.06
    íĨłíĨł
    0.06
     overview
    0.06
    Activations Density 0.001%

    No Known Activations