© 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. 106114
    Prev
    Next
    INDEX
    Explanations

    discussions related to legal proceedings and medical interventions in crisis situations

    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
     secular
    -0.07
    atra
    -0.06
     official
    -0.06
     Killing
    -0.06
    illac
    -0.06
    ccoli
    -0.06
    ombres
    -0.06
    ystone
    -0.06
    official
    -0.05
    azen
    -0.05
    POSITIVE LOGITS
    /respond
    0.07
    efa
    0.07
    osg
    0.07
     بÙĨد
    0.07
    ÑĥÑĩа
    0.07
    عاÙĨ
    0.06
    .CodeAnalysis
    0.06
    lops
    0.06
     Stateless
    0.06
    -initialized
    0.06
    Activations Density 0.008%

    No Known Activations