© 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. 15-LLAMASCOPE-RES-131K
    11. 27274
    Prev
    Next
    INDEX
    Explanations

    conditional phrases related to recommendations and evaluations

    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
    hu
    -0.08
    ales
    -0.07
    erg
    -0.07
    bu
    -0.06
    ossip
    -0.06
    acey
    -0.06
    elle
    -0.06
    fte
    -0.06
    aled
    -0.06
    otton
    -0.06
    POSITIVE LOGITS
     Canter
    0.08
     Conj
    0.06
    .Generation
    0.06
    Gatt
    0.06
     ^↵
    0.06
    }}],↵
    0.06
    cona
    0.06
     dim
    0.06
     PyErr
    0.06
     conj
    0.05
    Activations Density 0.017%

    No Known Activations