© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 89508
    Prev
    Next
    INDEX
    Explanations

    the name "Greg," indicating references to a specific person in various contexts

    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
    WithError
    -0.07
    éru
    -0.07
    iggins
    -0.06
    bast
    -0.06
    _Common
    -0.06
    storybook
    -0.06
    intr
    -0.06
    ancock
    -0.06
    ëĿ½
    -0.06
     OnCollision
    -0.06
    POSITIVE LOGITS
    ory
    0.13
    orio
    0.10
    orian
    0.10
    oire
    0.09
    erson
    0.09
    ORY
    0.09
    arious
    0.09
    ori
    0.08
    orious
    0.08
    oria
    0.08
    Activations Density 0.007%

    No Known Activations