© 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. 127216
    Prev
    Next
    INDEX
    Explanations

    content that discusses music or entertainment rankings and lists

    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
    Å¡ov
    -0.09
    pedia
    -0.08
    osyal
    -0.08
    rchive
    -0.08
     Incontri
    -0.08
    orsk
    -0.08
    ÑĢÑıдÑĥ
    -0.08
    Ģ
    -0.08
    ůj
    -0.07
    меÑĩ
    -0.07
    POSITIVE LOGITS
     discuss
    0.09
     talk
    0.09
     listener
    0.08
     discusses
    0.08
     discussion
    0.07
     tons
    0.07
     we
    0.07
     segment
    0.07
     discussing
    0.07
     briefly
    0.07
    Activations Density 0.009%

    No Known Activations