© 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. 30309
    Prev
    Next
    INDEX
    Explanations

    phrases related to being prepared or having necessary resources

    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
    ely
    -0.07
    ä¸ĸç´Ģ
    -0.07
     пÑĸÑĪ
    -0.07
    ãĤ¤ãĥĪ
    -0.07
    IVERS
    -0.07
     Kane
    -0.07
    Ñİк
    -0.07
    ÑģоÑĤ
    -0.07
    kud
    -0.06
    arial
    -0.06
    POSITIVE LOGITS
    ments
    0.09
    å¤ĩ
    0.08
    ment
    0.07
    381
    0.07
    MENTS
    0.07
    rement
    0.06
     multiline
    0.06
    idity
    0.06
    ally
    0.06
     facilities
    0.06
    Activations Density 0.009%

    No Known Activations