© 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. 127770
    Prev
    Next
    INDEX
    Explanations

    phrases referring to optimal solutions or plans

    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
    liness
    -0.07
    们
    -0.06
    اÙģت
    -0.06
    esses
    -0.06
    ields
    -0.06
    emes
    -0.06
    ess
    -0.06
    he
    -0.06
    essel
    -0.06
    eme
    -0.06
    POSITIVE LOGITS
     sayıda
    0.09
    imum
    0.09
    imal
    0.09
    /opt
    0.09
    /original
    0.09
    ities
    0.08
    IMUM
    0.08
    istic
    0.08
    ungeons
    0.08
    conditions
    0.07
    Activations Density 0.008%

    No Known Activations