© 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. 76181
    Prev
    Next
    INDEX
    Explanations

    instances of violence and atrocities, particularly in a military context

    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
    .gov
    -0.06
    opis
    -0.06
    lescope
    -0.06
    ueur
    -0.06
    weak
    -0.06
     weak
    -0.06
    cool
    -0.06
    OMET
    -0.05
    sworth
    -0.05
    ving
    -0.05
    POSITIVE LOGITS
     exception
    0.13
     exceptions
    0.13
     exceptional
    0.12
     Exception
    0.11
     rarity
    0.11
    exceptions
    0.10
     rare
    0.10
    exception
    0.10
     Exceptions
    0.10
     EXCEPTION
    0.10
    Activations Density 0.044%

    No Known Activations