© 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. 22-LLAMASCOPE-RES-131K
    11. 4185
    Prev
    Next
    INDEX
    Explanations

    future promises or predictions related to outcomes and agreements

    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
     Hlav
    -0.07
     ampl
    -0.07
     Ampl
    -0.07
    ãn
    -0.07
     Hindered
    -0.07
    stery
    -0.07
    ender
    -0.07
     amplify
    -0.07
    chrome
    -0.07
    nda
    -0.06
    POSITIVE LOGITS
     help
    0.11
     helps
    0.09
     helfen
    0.09
     allow
    0.09
     enable
    0.09
     allows
    0.09
    help
    0.08
    allow
    0.08
     benefit
    0.08
     enables
    0.08
    Activations Density 0.029%

    No Known Activations