© 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. 54538
    Prev
    Next
    INDEX
    Explanations

    phrases that express permanence or impossibility regarding actions or states

    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
    -valu
    -0.07
     å®
    -0.07
    ä»ĺãģį
    -0.07
    rech
    -0.07
    ExecutionContext
    -0.07
    æľĢåĪĿ
    -0.06
    anken
    -0.06
     Fra
    -0.06
     ölüm
    -0.06
    llib
    -0.06
    POSITIVE LOGITS
     be
    0.07
    143
    0.07
     again
    0.07
     permanently
    0.07
    theless
    0.07
    atori
    0.06
    yro
    0.06
    155
    0.06
    /be
    0.06
     fully
    0.06
    Activations Density 0.016%

    No Known Activations