© 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. 106744
    Prev
    Next
    INDEX
    Explanations

    references to specific versions of the Windows operating system

    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
    icher
    -0.07
    ohana
    -0.06
    翼
    -0.06
    оÑĢÑĥж
    -0.06
    idar
    -0.06
     Roth
    -0.05
     Stat
    -0.05
    éĤ£ä¹Ī
    -0.05
    MBED
    -0.05
    .âĢ¦
    -0.05
    POSITIVE LOGITS
    istrovstvÃŃ
    0.08
     Wikispecies
    0.07
    437
    0.07
    gnore
    0.07
    rial
    0.07
     (*((
    0.07
    Ign
    0.06
    ctal
    0.06
    NSNotification
    0.06
    collections
    0.06
    Activations Density 0.000%

    No Known Activations