© 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. 83796
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and expressions of sentiment

    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
    argas
    -0.08
    kud
    -0.08
    ismet
    -0.08
    ROTO
    -0.07
     sperma
    -0.07
    oggler
    -0.07
    toi
    -0.07
    _SENS
    -0.07
    ApiResponse
    -0.07
    Äįet
    -0.07
    POSITIVE LOGITS
     fill
    0.11
     gaps
    0.10
     filled
    0.10
     fills
    0.09
     Fill
    0.09
     gap
    0.09
     filling
    0.09
     hollow
    0.08
     with
    0.08
    fill
    0.08
    Activations Density 0.024%

    No Known Activations