© 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. 93304
    Prev
    Next
    INDEX
    Explanations

    commands and references related to deleting or removing files and data

    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
    ToPoint
    -0.07
    /server
    -0.06
    OrDefault
    -0.06
    ÙĪار
    -0.06
     ãĥ©
    -0.06
    Mix
    -0.06
    690
    -0.06
    esar
    -0.06
    amburger
    -0.06
     plais
    -0.06
    POSITIVE LOGITS
     entire
    0.09
    /delete
    0.08
     traces
    0.08
    (delete
    0.08
    /Delete
    0.08
    ocache
    0.07
    inea
    0.07
    /remove
    0.07
     delete
    0.06
     unwanted
    0.06
    Activations Density 0.010%

    No Known Activations