© 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. 9-LLAMASCOPE-RES-131K
    11. 96718
    Prev
    Next
    INDEX
    Explanations

    words related to physical journeys or trekking experiences

    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
    orry
    -0.07
    459
    -0.07
    RAIN
    -0.06
    jerne
    -0.06
    berger
    -0.06
    lain
    -0.06
    453
    -0.06
    577
    -0.06
    orthand
    -0.06
    sta
    -0.06
    POSITIVE LOGITS
    ê°IJ
    0.07
    Ãły
    0.07
    íķ
    0.07
    ìļ°ë¦¬
    0.07
    _COMPARE
    0.07
     McGr
    0.06
    izik
    0.06
    .until
    0.06
     güncel
    0.06
    elay
    0.06
    Activations Density 0.018%

    No Known Activations