© 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. 71799
    Prev
    Next
    INDEX
    Explanations

    specific names or terms associated with locations and geographical 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
     Trom
    -0.06
    sss
    -0.06
    Scrollbar
    -0.06
    arty
    -0.06
    izr
    -0.06
    InnerHTML
    -0.06
    lrt
    -0.06
    olor
    -0.06
    uur
    -0.05
    innie
    -0.05
    POSITIVE LOGITS
    anian
    0.12
    onian
    0.09
    ensis
    0.09
    opolitan
    0.09
    sonian
    0.08
    arian
    0.08
    adian
    0.07
     Vie
    0.07
    ense
    0.07
    apore
    0.07
    Activations Density 0.026%

    No Known Activations