© 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. 60432
    Prev
    Next
    INDEX
    Explanations

    references to significant events or experiences related to societal issues

    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
    reeze
    -0.07
    yte
    -0.07
     indir
    -0.07
    ifo
    -0.06
    307
    -0.06
    ãģĻãĤĮãģ°
    -0.06
    iego
    -0.06
    ilit
    -0.06
    ixin
    -0.06
    atron
    -0.06
    POSITIVE LOGITS
     causes
    0.08
    导èĩ´
    0.08
    éĢłæĪIJ
    0.08
    pcf
    0.07
     requires
    0.07
     Causes
    0.07
     creates
    0.07
    è¦ģæ±Ĥ
    0.06
     naturally
    0.06
     demands
    0.06
    Activations Density 0.047%

    No Known Activations