© 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. 3193
    Prev
    Next
    INDEX
    Explanations

    the name "Sadler" and related variations

    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
    oru
    -0.07
    ception
    -0.07
    iola
    -0.07
    озд
    -0.06
    ensi
    -0.06
     æĸ¼
    -0.06
    æ³
    -0.06
    mighty
    -0.06
    ç§Ģ
    -0.06
    .PLL
    -0.06
    POSITIVE LOGITS
    yre
    0.07
    chez
    0.07
    ma
    0.07
    StringValue
    0.07
    wick
    0.07
    ynam
    0.07
    akah
    0.07
    ellite
    0.06
    ur
    0.06
     stol
    0.06
    Activations Density 0.017%

    No Known Activations