© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 62663
    Prev
    Next
    INDEX
    Explanations

    expressions of enjoyment and positive experiences in social settings

    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
    atl
    -0.06
    .mat
    -0.06
     cyclists
    -0.06
     Strength
    -0.06
    eç
    -0.06
    _strength
    -0.06
     strength
    -0.05
     eser
    -0.05
     haunt
    -0.05
     strong
    -0.05
    POSITIVE LOGITS
     fun
    0.26
     FUN
    0.21
    fun
    0.20
     Fun
    0.20
    Fun
    0.19
    FUN
    0.19
    .fun
    0.17
    (fun
    0.17
    	fun
    0.17
     enjoyable
    0.15
    Activations Density 0.119%

    No Known Activations