© 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. 74596
    Prev
    Next
    INDEX
    Explanations

    phrases that praise or characterize performances and albums

    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
    amerate
    -0.07
    rowable
    -0.07
    swer
    -0.07
    ardy
    -0.07
    Animating
    -0.07
    @student
    -0.07
    ahas
    -0.07
    buz
    -0.07
    NCY
    -0.06
     Wein
    -0.06
    POSITIVE LOGITS
    icari
    0.07
    _GEN
    0.06
     Overall
    0.06
     overall
    0.06
     Borders
    0.06
    ONGL
    0.05
     impressed
    0.05
     rare
    0.05
     Homo
    0.05
     mark
    0.05
    Activations Density 0.012%

    No Known Activations