© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 57557
    Prev
    Next
    INDEX
    Explanations

    indicators of upcoming content or events

    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
     Py
    -0.06
    orer
    -0.06
    ::~
    -0.05
     Tro
    -0.05
    ás
    -0.05
     Nimbus
    -0.05
     Giant
    -0.05
    é¡Į
    -0.05
    stre
    -0.05
    ä¸ĺ
    -0.05
    POSITIVE LOGITS
    ÅĻÃŃz
    0.08
    isson
    0.08
     wr
    0.07
    hsi
    0.07
    akest
    0.07
     jezd
    0.07
    engeance
    0.07
    çĩ
    0.07
    Æ°
    0.07
    imler
    0.07
    Activations Density 0.001%

    No Known Activations