© 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. 152
    Prev
    Next
    INDEX
    Explanations

    references to talent and abilities in various contexts

    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
    abis
    -0.08
    akh
    -0.07
    ardy
    -0.07
    imat
    -0.07
    ault
    -0.07
    allon
    -0.07
    menin
    -0.07
    reo
    -0.07
    entar
    -0.07
    uess
    -0.07
    POSITIVE LOGITS
     early
    0.07
     talent
    0.07
    æĹ©
    0.07
     unusual
    0.07
     natur
    0.06
     développ
    0.06
     nature
    0.06
    early
    0.06
     hypers
    0.06
     inn
    0.06
    Activations Density 0.020%

    No Known Activations