© 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 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. 93877
    Prev
    Next
    INDEX
    Explanations

    phrases indicating capability or potential action

    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
    ILINE
    -0.06
    alam
    -0.06
     patron
    -0.05
    chein
    -0.05
     Liberation
    -0.05
     know
    -0.05
     setId
    -0.05
     ==============================================================
    -0.05
     directly
    -0.05
     Caul
    -0.05
    POSITIVE LOGITS
    215
    0.08
    adel
    0.07
     handle
    0.07
    opi
    0.07
    ade
    0.07
    handle
    0.07
    ocale
    0.07
     udrž
    0.07
    æĪIJåĬŁ
    0.07
    HING
    0.07
    Activations Density 0.033%

    No Known Activations