© 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. 106747
    Prev
    Next
    INDEX
    Explanations

    phrases indicating denial, blame, and justifications for actions related to conflict or violence

    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
    .scalablytyped
    -0.09
    ripper
    -0.08
    ATIC
    -0.08
    IFn
    -0.07
    \<^
    -0.07
    ilmiÅŁtir
    -0.07
    çľł
    -0.07
    hydrate
    -0.07
    /Dk
    -0.07
    irket
    -0.07
    POSITIVE LOGITS
     wonder
    0.12
     then
    0.10
     Wonder
    0.10
     wondered
    0.09
     wondering
    0.09
    Wonder
    0.09
     when
    0.08
     blame
    0.08
     wonders
    0.08
     THEN
    0.08
    Activations Density 0.031%

    No Known Activations