© 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. 83200
    Prev
    Next
    INDEX
    Explanations

    mentions of prestigious awards and recognitions in various fields

    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
    icas
    -0.07
    assin
    -0.06
     поÑģл
    -0.06
     versch
    -0.06
    Å¡ÃŃ
    -0.06
    ibase
    -0.06
    raki
    -0.06
    isko
    -0.06
    ometr
    -0.06
    arker
    -0.06
    POSITIVE LOGITS
    iron
    0.06
    ena
    0.06
    unal
    0.06
     Battlefield
    0.06
    lava
    0.06
    unner
    0.06
    paced
    0.06
    201
    0.06
    357
    0.06
    adiator
    0.06
    Activations Density 0.008%

    No Known Activations