© 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. 4343
    Prev
    Next
    INDEX
    Explanations

    instances of the word "all" and variations of time 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
     ÑģÑĤÑĢ
    -0.07
    edin
    -0.06
    lun
    -0.06
    .wik
    -0.06
    èĭ
    -0.06
    uel
    -0.06
    .nr
    -0.06
    ior
    -0.06
    utin
    -0.06
    lar
    -0.05
    POSITIVE LOGITS
    dü
    0.07
    iyat
    0.06
    buat
    0.06
    Bind
    0.06
    pio
    0.06
    erde
    0.06
    ázd
    0.06
     KD
    0.06
    (æľ¨
    0.06
    Å¡ov
    0.06
    Activations Density 0.000%

    No Known Activations