© 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. 119382
    Prev
    Next
    INDEX
    Explanations

    terms related to military strategy and operations

    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
    AZY
    -0.06
    ocoa
    -0.06
    ftware
    -0.06
     talk
    -0.06
    408
    -0.06
     Talk
    -0.06
     contrary
    -0.06
     vitae
    -0.05
    RAY
    -0.05
     steer
    -0.05
    POSITIVE LOGITS
     missions
    0.08
    664
    0.07
    LEX
    0.07
    ůj
    0.07
    issance
    0.07
     assets
    0.06
    _FM
    0.06
    oldur
    0.06
     Juliet
    0.06
    ensively
    0.06
    Activations Density 0.005%

    No Known Activations