© 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. 3259
    Prev
    Next
    INDEX
    Explanations

    references to intentionality and planned actions

    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
     cavity
    -0.06
     blind
    -0.06
    NK
    -0.06
    alue
    -0.05
    zac
    -0.05
     cav
    -0.05
     astr
    -0.05
    lename
    -0.05
    nez
    -0.05
     pract
    -0.05
    POSITIVE LOGITS
     intentional
    0.22
     deliberate
    0.19
     intentionally
    0.17
     purpose
    0.15
     deliberately
    0.14
     purposely
    0.14
    purpose
    0.13
     Purpose
    0.13
    -purpose
    0.12
     PURPOSE
    0.12
    Activations Density 0.088%

    No Known Activations