© 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. 78609
    Prev
    Next
    INDEX
    Explanations

    phrases indicating potential outcomes or predictions related to profitability and success

    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
     Berger
    -0.06
     bar
    -0.06
     offshore
    -0.06
     Templ
    -0.06
     Sever
    -0.06
     unofficial
    -0.06
     sever
    -0.05
     Mar
    -0.05
    poser
    -0.05
     Norman
    -0.05
    POSITIVE LOGITS
     ÙģرÙĪدگاÙĩ
    0.09
    åĽ
    0.08
    anter
    0.07
    .twig
    0.07
    ptions
    0.07
    hlas
    0.07
    ichni
    0.07
     MÄĽst
    0.07
    άÏģÏĩ
    0.07
    ục
    0.07
    Activations Density 0.001%

    No Known Activations