© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 14634
    Prev
    Next
    INDEX
    Explanations

    concepts related to copyright infringement and media ownership

    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
    zim
    -0.07
    riger
    -0.07
    inged
    -0.07
     retr
    -0.07
     prototypes
    -0.06
     proto
    -0.06
    åĺī
    -0.06
    avou
    -0.06
    onom
    -0.06
    avad
    -0.06
    POSITIVE LOGITS
    istrovstvÃŃ
    0.07
     Windsor
    0.06
    enou
    0.06
    ActionCreators
    0.06
    .Generated
    0.06
    翼
    0.06
     XCT
    0.06
    à¹ģà¸Ī
    0.06
     EOF
    0.06
    venue
    0.06
    Activations Density 0.001%

    No Known Activations