© 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. 57260
    Prev
    Next
    INDEX
    Explanations

    phrases indicating varying levels of expectations

    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
    MAND
    -0.07
    ове
    -0.07
    wor
    -0.06
    pert
    -0.06
    mand
    -0.06
     Pert
    -0.06
     to
    -0.06
     pert
    -0.06
    go
    -0.06
    ady
    -0.06
    POSITIVE LOGITS
     expectations
    0.10
     expectation
    0.08
     Expect
    0.08
    Expect
    0.07
    ìĤ¬íķŃ
    0.07
    ãĥ¼ãĥĨ
    0.07
     gap
    0.07
    sWith
    0.07
    illy
    0.07
     ìĤ¬íķŃ
    0.07
    Activations Density 0.005%

    No Known Activations