© 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. 17-LLAMASCOPE-RES-131K
    11. 17223
    Prev
    Next
    INDEX
    Explanations

    qualifications and requirements for job candidates

    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
     reserve
    -0.06
    ="__
    -0.06
    arie
    -0.06
    esian
    -0.06
    XS
    -0.05
     Episode
    -0.05
    /bin
    -0.05
    lated
    -0.05
    Transient
    -0.05
    atorium
    -0.05
    POSITIVE LOGITS
     possess
    0.09
    ød
    0.08
    Ùģس
    0.08
    çĨŁ
    0.07
    ynos
    0.07
    regon
    0.07
     minimum
    0.07
    kladnÃŃ
    0.07
     modne
    0.07
    rrha
    0.07
    Activations Density 0.006%

    No Known Activations