Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96253
    Prev
    Next
    INDEX
    Explanations

    references to military actions and casualties related to drone strikes

    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
    ptal
    -0.06
    ica
    -0.06
    onde
    -0.06
    lopen
    -0.06
     Lyon
    -0.06
     merc
    -0.06
     dist
    -0.06
    ola
    -0.05
    ia
    -0.05
    coop
    -0.05
    POSITIVE LOGITS
    mil
    0.07
     McN
    0.06
    _flutter
    0.06
    ỹ
    0.06
    agues
    0.06
    Sharper
    0.06
    alom
    0.06
    uras
    0.06
    ONUS
    0.06
    .Abstractions
    0.06
    Activations Density 0.024%

    No Known Activations