© 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. 77862
    Prev
    Next
    INDEX
    Explanations

    queries about expressions of sympathy and personal preferences

    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
    rv
    -0.07
    äm
    -0.07
    ree
    -0.07
    duk
    -0.07
    ally
    -0.06
    itational
    -0.06
     ours
    -0.06
     VÅ¡
    -0.06
     rele
    -0.06
     rec
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.10
     Currently
    0.06
    letic
    0.06
    urrent
    0.06
    boro
    0.06
     наÑıв
    0.06
    \S
    0.06
    /classes
    0.06
    andles
    0.06
     {{{
    0.06
    Activations Density 0.002%

    No Known Activations