© 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. 78743
    Prev
    Next
    INDEX
    Explanations

    references to viewing or interpreting experiences through various perspectives or lenses

    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
    ihan
    -0.08
    elan
    -0.08
    elib
    -0.08
    abbo
    -0.08
    uida
    -0.07
    izza
    -0.07
    utow
    -0.07
     вÑĤ
    -0.07
    greg
    -0.07
    eward
    -0.07
    POSITIVE LOGITS
     view
    0.10
     perspective
    0.10
    view
    0.09
    -view
    0.09
     lenses
    0.09
     lens
    0.09
     eyes
    0.09
    -eye
    0.09
     View
    0.08
     VIEW
    0.08
    Activations Density 0.031%

    No Known Activations