© 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. 59584
    Prev
    Next
    INDEX
    Explanations

    mentions of the Redux library

    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
    emer
    -0.07
    iface
    -0.06
     provisional
    -0.06
    oyer
    -0.06
    md
    -0.06
     command
    -0.06
     cr
    -0.06
     till
    -0.06
    ha
    -0.05
    handled
    -0.05
    POSITIVE LOGITS
    ãĤĤãĤĬ
    0.07
    éĿĪ
    0.07
    ocity
    0.07
    ÑģÑıÑĩ
    0.07
    htable
    0.07
    uhn
    0.07
    á»iji
    0.07
    ÅĻich
    0.06
     declar
    0.06
    INA
    0.06
    Activations Density 0.000%

    No Known Activations