© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 90607
    Prev
    Next
    INDEX
    Explanations

    references to hip hop music and its cultural significance

    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
     gap
    -0.06
     Gap
    -0.06
     Ñĥли
    -0.06
     peak
    -0.06
    phant
    -0.06
     Ent
    -0.06
    inct
    -0.06
    ÙĥÙĪ
    -0.05
    linger
    -0.05
     larger
    -0.05
    POSITIVE LOGITS
    urable
    0.07
    ahr
    0.07
    ábado
    0.07
    eya
    0.06
    nable
    0.06
    267
    0.06
    pod
    0.06
    'gc
    0.06
    åŀ
    0.06
    .er
    0.06
    Activations Density 0.090%

    No Known Activations