© 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. 59867
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols in the text

    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
    çak
    -0.07
    umlu
    -0.07
    uchen
    -0.07
    tid
    -0.06
    atı
    -0.06
    大åħ¨
    -0.06
    _DEPRECATED
    -0.06
    illac
    -0.06
    etto
    -0.06
    ãĥ£
    -0.06
    POSITIVE LOGITS
    åľĴ
    0.07
    acket
    0.06
    onian
    0.06
    ê»
    0.06
     ãģª
    0.06
    à¤Ľ
    0.06
     motion
    0.05
    Constants
    0.05
     Park
    0.05
    tual
    0.05
    Activations Density 0.007%

    No Known Activations