© 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. 84786
    Prev
    Next
    INDEX
    Explanations

    concepts related to change and transitions

    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
    ogn
    -0.07
    ç´
    -0.06
    owan
    -0.06
    aná
    -0.06
    onto
    -0.06
    ustomer
    -0.06
    íĩ´
    -0.06
    åı
    -0.06
    757
    -0.06
    exels
    -0.06
    POSITIVE LOGITS
     so
    0.15
     neither
    0.13
     likewise
    0.12
    Neither
    0.12
     Neither
    0.12
     Likewise
    0.11
     Dit
    0.10
    itto
    0.10
    Lik
    0.09
    éĤ£ä¹Ī
    0.08
    Activations Density 0.076%

    No Known Activations