© 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. 77354
    Prev
    Next
    INDEX
    Explanations

    expressions of mixed emotions and real-life struggles

    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
    xis
    -0.06
    yll
    -0.06
    abyrinth
    -0.06
    orse
    -0.06
    umping
    -0.06
    ickest
    -0.06
    zin
    -0.06
    #error
    -0.06
    iddi
    -0.06
    ifa
    -0.06
    POSITIVE LOGITS
     modern
    0.08
     interpret
    0.08
    pects
    0.08
     interpretation
    0.08
     interpreted
    0.07
    modern
    0.07
     import
    0.07
    çݰ代
    0.07
     Interpreter
    0.07
     interp
    0.07
    Activations Density 0.029%

    No Known Activations