© 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. 9-LLAMASCOPE-RES-131K
    11. 95276
    Prev
    Next
    INDEX
    Explanations

    references to specific episodes or segments in a podcast series

    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
     exact
    -0.06
     oc
    -0.06
    ush
    -0.06
    res
    -0.05
    ep
    -0.05
    ours
    -0.05
    opes
    -0.05
    omer
    -0.05
    avi
    -0.05
     map
    -0.05
    POSITIVE LOGITS
    ëŁ
    0.09
    onu
    0.09
    flux
    0.08
    BoxLayout
    0.08
    ToString
    0.08
    wu
    0.08
    gage
    0.08
    ignum
    0.08
    .segment
    0.07
    ProcAddress
    0.07
    Activations Density 0.008%

    No Known Activations