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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 107195
    Prev
    Next
    INDEX
    Explanations

    actions related to destruction, removal, or alteration of structures

    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
    idor
    -0.07
    anches
    -0.07
    570
    -0.07
     dosy
    -0.07
    ronic
    -0.07
    ivery
    -0.07
    ãĥĥãĥī
    -0.07
    immel
    -0.06
    funcs
    -0.06
    xfc
    -0.06
    POSITIVE LOGITS
    erp
    0.08
    ÄŁit
    0.07
     entirely
    0.06
    olle
    0.06
     inward
    0.06
     prepar
    0.06
     Gle
    0.06
    itelist
    0.06
    erson
    0.06
     khá»ıi
    0.06
    Activations Density 0.023%

    No Known Activations