© 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. 87480
    Prev
    Next
    INDEX
    Explanations

    words related to the Earth and its regions

    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
    orie
    -0.07
    ếp
    -0.07
    iger
    -0.06
    oeff
    -0.06
    eyer
    -0.06
    sonian
    -0.06
    erot
    -0.06
    à¹Ģà¸ģà¸Ńร
    -0.06
    yer
    -0.06
    peria
    -0.06
    POSITIVE LOGITS
    -wide
    0.14
    /world
    0.10
    wide
    0.09
    esimal
    0.07
     earth
    0.07
    lun
    0.07
    -span
    0.07
    éĻħ
    0.07
    à¥Ģय
    0.07
    -long
    0.07
    Activations Density 0.012%

    No Known Activations