© 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. 16223
    Prev
    Next
    INDEX
    Explanations

    phrases related to mitigation and softening of tensions or impacts

    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
    amina
    -0.08
    'gc
    -0.07
    .mdl
    -0.07
     lẫn
    -0.07
    .define
    -0.06
     Malone
    -0.06
    gnore
    -0.06
    ifar
    -0.06
    Combat
    -0.06
    Ïģκε
    -0.06
    POSITIVE LOGITS
     otherwise
    0.10
     impact
    0.09
    impact
    0.08
    otherwise
    0.07
     Otherwise
    0.07
    /mit
    0.07
     impacts
    0.07
     sting
    0.07
     effects
    0.07
     OTHERWISE
    0.07
    Activations Density 0.025%

    No Known Activations