© 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. 119319
    Prev
    Next
    INDEX
    Explanations

    references to the influence and legacy of individuals, particularly in the context of art and law

    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
     trump
    -0.08
    Logic
    -0.07
    oplevel
    -0.07
    _mirror
    -0.06
    303
    -0.06
    ando
    -0.06
    irsch
    -0.06
    odo
    -0.06
    cket
    -0.06
    íıIJ
    -0.06
    POSITIVE LOGITS
     influence
    0.13
     Influence
    0.12
     contribution
    0.11
     contributions
    0.11
     impact
    0.10
     Impact
    0.10
    å½±åĵį
    0.09
    impact
    0.09
     legacy
    0.09
    Impact
    0.09
    Activations Density 0.030%

    No Known Activations