© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 77308
    Prev
    Next
    INDEX
    Explanations

    instances of numerical or statistical data references

    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
     Zika
    -0.07
     Poke
    -0.07
     theano
    -0.07
    ena
    -0.06
    gv
    -0.06
    oreal
    -0.06
    á»Ļt
    -0.06
    201
    -0.06
    vere
    -0.06
    Äįel
    -0.06
    POSITIVE LOGITS
    202
    0.10
    Û²Û°Û²
    0.07
     covid
    0.07
     Biden
    0.07
    itesi
    0.07
     Fully
    0.06
     Covid
    0.06
    asury
    0.06
    _PARTITION
    0.06
     Collins
    0.06
    Activations Density 0.025%

    No Known Activations