© 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. 16140
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial investments and investment strategies

    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
    út
    -0.08
    idden
    -0.07
    ún
    -0.07
    idar
    -0.07
    byss
    -0.07
    REATE
    -0.06
    liers
    -0.06
    lier
    -0.06
    flush
    -0.06
    ombre
    -0.06
    POSITIVE LOGITS
    dia
    0.07
    ekil
    0.06
    ih
    0.06
    sel
    0.06
    iah
    0.06
    zym
    0.06
    ito
    0.06
    _submenu
    0.06
    ECTOR
    0.06
    765
    0.06
    Activations Density 0.009%

    No Known Activations